Circuits in Language Models

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

Jul 28, 2026cs.LG

LLMs Can Annotate Attribution Graphs

Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step of grouping individual features or MLP neurons into supernodes. We present a simple pipeline for automating this step: directly presenting feature descriptions to a language model that groups them into supernodes. Using automated interpretability metrics, we confirm that supernodes generated by our pipeline are as interpretable as those generated by human annotators. On a two-hop Capitals task, our pipeline recovers a supernode corresponding to the intermediate hop in 97 of 100 prompts. Finally, we present a simple proof of concept using our pipeline for open-ended exploration, where we automatically annotate 1000 attribution graphs from Wikipedia prompt completions and then use an LLM judge to flag interesting graphs worth human review. We hope this work demonstrates that even simple automation can produce meaningful attribution graph annotations, motivating further work on automated circuit tracing.

Ameen Patel, Max Zhang, Nathan Hu

Stanford University

LLM Interpretability LLM-Assisted Annotation Circuits in Language Models

Jul 23, 2026cs.CL

What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations

Do independently trained language models come to represent the same thing in the same way? We answer for code, extending a recently introduced concept-circuit extraction method to a 2x2 design -- Python and Rust crossed with Qwen2.5-Coder-7B and DeepSeek-Coder-V1-6.7B -- and measuring a complete inventory of grammatical concepts (58 Python, 57 Rust) identically in all four cells: the smallest design that separates what depends on the task, the language, and the model. The answer splits into three parts. What earns dedicated circuitry is set by the task: the models agree on which concepts receive circuits (Spearman

ρ

= 0.638 for Python, 0.673 for Rust, both p <

10^{-7}

). Where those circuits sit is set by the model: Qwen processes concepts in a late band (~L17-19), DeepSeek at L6-7, for both languages. How circuits grow across layers is also set by the model: Qwen gives its atomic concepts an early spike that DeepSeek does not. "Are circuits universal?" thus has no single answer: yes for What, no for Where and How -- universality is a property of representational content, not of computational organisation. None of this structure was fixed in advance. The agreement could have landed anywhere between independence and identity; it lands at

ρ\approx 0.65

. Rust constructs receive 2-3x more concept-specific circuitry than their Python equivalents, in both models. Both models share neurons between the languages (6/7 and 7/7 paired constructs), DeepSeek 1.94x more than Qwen -- a direction no prior result predicts. And Qwen binds nine keywords of Rust's type-and-trait machinery into one tight neuron cluster (Jaccard 0.535 vs null 0.112, p < 0.001), a semantic dimension invisible in surface syntax. Ablation and linear probes confirm the circuits are functional. All claims are scoped to this 2x2; whether the per-model profile predicts a third model is the designed next test.

Piotr Wilam

University College London

Circuit Discovery Language Model Introspection Circuits in Language Models Representation Geometry in Language Models Code Language Models

Jul 23, 2026cs.CL

Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept

Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex selectional constraints and contextual cues, such as verb-argument interactions. Yet, current large language models (LLMs) appear to be capable of doing it. We investigate whether this animacy-sensitive behavior of LLMs can be traced to a localized set of causally relevant components and connections. To do so, we construct a controlled dataset of minimal pairs and perform circuit discovery on four open-weight models. Through in-depth experiments and ablations, we show that a causal mechanism responsible for handling animacy in these models does exist, thus discovering an animacy circuit. At the same time, this circuit appears to be less localized compared to other known ones and generalizes only partially across models and animacy tasks, confirming the distributed, context-dependent, and somewhat graded nature of the animacy concept.

Samuele Punzo, Giovanni Cinà, Sandro Pezzelle

Graduate School of Informatics, University of Amsterdam · Department of Medical Informatics, Amsterdam University Medical Center · ILLC, University of Amsterdam

LLM Interpretability Circuits in Language Models Causal Interventions in Language Models

Jul 21, 2026cs.LG

CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability

Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implementations for discovery, evaluation, and intervention, as well as hand-authoring the contrastive prompts required by many discovery methods. This fragmentation makes methods difficult to compare and limits their application beyond canonical tasks. We introduce CircuitKIT, a source-available library that connects the circuit-analysis workflow through a typed, serializable representation. CircuitKIT provides a suite of discovery algorithms, declarative interfaces for mapping structured data into discovery tasks, complementary circuit diagnostics, and downstream application modules. Together, these components provide common infrastructure for conducting and comparing circuit analyses. The library, examples, notebooks, and documentation are released at https://github.com/Lexsi-Labs/CircuitKIT .

Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1

Lexsi Labs

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Explainability Evaluation

Jul 21, 2026cs.LG

Circuit Claims Depend on What Is Extracted and How It Is Compared

Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior. We argue that this reading is under-determined: preserving behavior does not single out one circuit, because the claim it supports depends on which circuit is reported and how two circuits are compared. We make this concrete in a synthetic Lean tactic-prediction benchmark -- predicting the next step of a proof -- where fixed proof rules with randomized surface form let differences between extracted circuits be attributed to these choices rather than to the task. Across dense and weight-sparse checkpoints (most weights constrained to zero) of the same transformer, evaluated on atomic (single-rule) and compositional (multi-rule) proofs, we vary which extracted object is reported (a compact prediction-preserving circuit, a broader graph that also keeps surrounding read, write, and routing structure, or the smallest subgraph meeting a post-ablation loss threshold), and whether each attention head's query and key are represented jointly or separately. Exact component-to-component edge overlap is low and sensitive to these choices, at times dropping to a random baseline, while two coarser summaries stay stable: the set of selected attention heads, and the circuit-size ranking of conditions that differ in which supervised checkpoint initializes reinforcement learning (RL). The largest accuracy gains from RL on compositional proofs come with the most structure beyond the atomic circuits. A circuit-level claim is therefore well defined only once one states which circuit is reported, the pruning threshold used to extract it, and the level at which circuits are compared. We distill these requirements into a reporting practice for circuit-extraction studies.

Yang Sheng, Jie Fu

1Fudan University · 2Shanghai Innovation Institute · 3IQuest Research

Transformer Interpretability Circuit Discovery Circuits in Language Models

Jul 18, 2026cs.CL

Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs

Large language models often succeed on one formulation of a problem while failing on an equivalent formulation. Whether these failures arise from distinct internal circuits or different activation states of a shared circuit remains unknown. Recent mechanistic interpretability studies suggest that arithmetic in LLMs emerges from a "bag of heuristics," encoded by a sparse set of MLP neurons that represent distinct arithmetic strategies. We investigate whether arithmetic heuristic neurons are form-invariant across symbolic arithmetic, natural language word problems, and Python code in three Llama-3 models. In each format, we identify arithmetic heuristic neurons using a two-stage pipeline combining attribution patching and activation patching. A compact set of neurons is shared across all three formats, and targeted interventions show this shared circuit is both necessary and sufficient for late-layer arithmetic computation. Transferring the shared neurons' activations from a successful execution in one format to a failed execution in another recovers most incorrect predictions, exceeding 97% for addition and subtraction, indicating that cross-format failures arise from activation states rather than distinct circuits. Moreover, shared neurons consistently belong to the same heuristic families across formats, demonstrating that arithmetic computation in LLMs is largely form-invariant at the neuron level.

Sharath Naganna, Tanvir Ahmed Sijan, Uddipta Kalita

Indian Institute of Technology Bombay, Mumbai, India · Jahangirnagar University, Dhaka, Bangladesh · National Institute of Technology, Silchar, India

LLM Interpretability Circuits in Language Models LLM Mathematical Reasoning

Jul 17, 2026cs.CL

Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models

While the internal mechanisms of autoregressive (AR) transformers have been studied extensively, much less is known about diffusion language models (DLMs), an emerging alternative that generates text by iterative denoising. In this work, we study how DLMs implement induction, a mechanism behind in-context learning in which the model finds a repeated context and copies the token that followed it. Our analysis compares attention-only AR models and absorbing-mask DLMs with matched architectures. We find that DLMs learn a bidirectional induction circuit, where previous-token and next-token heads write local context into the residual stream and later induction heads use it to find and copy the answer from the matching source position. The circuit is direction-symmetric, working whether the source appears in the past or in the future. When only left context is visible, matching what an AR model sees, the DLM does not outperform its AR counterpart in induction capabilities. However, we observe it has stronger induction when both sides of the masked token are visible, pointing to bidirectional context access rather than a stronger one-sided mechanism. Beyond induction, we provide causal evidence that DLMs compute the global fraction of masked tokens and use it as an implicit timestep, even though they are given no explicit timestep embedding.

Andy Catruna, Emilian Radoi

National University of Science and Technology POLITEHNICA Bucharest · Academy of Romanian Scientists

Masked Diffusion Models In-Context Learning Circuits in Language Models Induction Heads

Jul 16, 2026cs.AI

Transcoders for Investigating Deception in Language Models

Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse deceptive behaviour in language models, a behaviour that poses a safety and security risk. Using a Qwen3-4B model with pre-trained transcoders, specifically per-layer transcoders (PLTs), we construct attribution graphs that capture feature activations and inter-feature dependencies, allowing circuit-level analysis of deception. Through feature steering and circuit analysis, we identified a dictionary of deception-related features and show that these features exert a stronger influence on deceptive outputs, as they produce predictable shifts between deceptive and non-deceptive responses. These findings suggest that deception emerges from internal model mechanisms and highlight the potential of transcoders for behavioural monitoring and early detection of security vulnerabilities related to malicious behaviours in language models.

Darius Lim, Nathan Leow, Xin Wei Chia

Home Team Science & Technology Agency (HTX) Singapore

Deception in Language Models Circuits in Language Models

Jul 14, 2026cs.CL

A Shared Subcircuit Lets LLMs Count Down Across Tasks

Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table. These are all tasks that language models can do that requires tracking how many tokens remain before a target. In this work, we identify in Llama-3.1-70B-Instruct a general mechanism for performing these tasks: a "countdown subcircuit" that compares the current position to a goal length and estimates the time remaining until then. We first isolate a countdown subcircuit in a controlled setting, in which the model is tasked with writing a fixed-length sentence ending in a specified word. We then investigate the geometry of the representations used by the subcircuit, and find that the subcircuit uses an identical motif previously identified in a frontier LLM on a separate task, thus suggesting that this motif is shared across models. Finally, we use unsupervised probing on a natural language dataset to find a variety of other tasks where this subcircuit is used, including tasks where the goal length is inferred from context rather than explicitly stated. Our work suggests that reverse-engineering subcircuits allows us to understand how behaviors generalize from a single example to many different tasks and even models.

Jacob Dunefsky, Wes Gurnee, Emmanuel Ameisen

Yale University · Anthropic

Circuit Discovery Circuits in Language Models

Jul 13, 2026cs.LG

Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks

We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning. In this class, we theoretically prove that the training dynamics of attention models can be confined to a highly interpretable, low-dimensional invariant manifold. On this manifold, the learning dynamics are captured by a handful of interpretable coordinates rather than millions of parameters, making both theoretical and empirical analysis more tractable. Using this framework, we characterize how data statistics govern the competition between in-context and in-weights learning, we study how random initializations determine the `winning' circuit when multiple solutions are possible, and we demonstrate that the coordinate frame associated with the manifold can be used to automatically detect which circuits have been learned in trained models. By casting circuit formation as a low-dimensional dynamical phenomenon, we take a step toward a predictive theory of how Transformers learn.

Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet +1

ETH Zurich · Stanford University

In-Context Learning Circuits in Language Models Neural Network Training Dynamics

Jul 11, 2026cs.CL

Belief-reality separation lives in routing over a shared value slot in language models

Capable language models hold what a character believes apart from what is true: told "Anna believes the cup is blue; in reality it is red," they answer blue about Anna and red about the world. Where in the computation does that separation live? We show it rests on two separable mechanisms at two positions. A generic value slot binds the attributed value. A router at the query position selects which frame, the character's belief or reality, a query reads out. Two routes fill the slot: an asserted belief, whose value the text supplies, binds in directly; a derived belief, whose value must be inferred from what the character could see, arrives by a visibility-gated lookback. A subspace trained on either route steers the other, and only the derived route depends on described visibility. The slot itself carries no belief-reality tag: intervening on it moves a reality readout as strongly as a belief one. The separation lives instead in a dissociated pair of routing subspaces, which flip a query between frames without injecting the donor's value. These results hold across three architectures, on stimuli de-confounded against theory-of-mind-benchmark shortcuts; the behavior itself emerges between 3B and 7B across five model families. This paper develops the single belief-reality axis in depth; a companion paper shows the same slot-and-router format is shared across the other non-actual contexts a sentence can open (counterfactual, fictional, temporal).

Oliver Steele, Jiangtao Wen, Yuxing Han

Tsinghua University · NYU Shanghai

Theory of Mind LLM Interpretability Circuits in Language Models Representation Geometry in Language Models

Jul 11, 2026cs.CL

One mechanism for many mental spaces: a shared router over a value slot in language models

Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive); Fauconnier's mental-space theory treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families; belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).

Oliver Steele, Jiangtao Wen, Yuxing Han

Tsinghua University · NYU Shanghai

LLM Interpretability Circuits in Language Models Representation Geometry in Language Models

Jul 8, 2026cs.LG

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning

This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks. While traditional explainable AI methods often stop at surface-level input-output correlations, this approach directly addresses the opaque "black box" nature of machine learning models, which is essential for ensuring safety and auditability in high-stakes deployments. The paper provides a detailed examination of Transformer circuit analysis, exploring how internal components like the residual stream, attention mechanisms, and induction heads drive complex tasks and in-context learning. It subsequently tackles the core challenge of superposition and polysemanticity, demonstrating how tools like Sparse Autoencoders (SAEs) and transcoders can decompose tangled network activations into distinct, human-interpretable features. Furthermore, the paper explores methods for actively controlling and modifying model behavior through steering vectors and causal interventions. Finally, it connects these mechanistic insights with neurosymbolic AI frameworks designed to translate neural representations into explicit, executable logical rules.

Pranav Sawant, Jakub Krejčí

The University of Texas at Dallas 800 W Campbell Rd, Richardson, TX 75080, United States · VSB—Technical University of Ostrava 708 00, Ostrava, Czech Republic

Transformer Interpretability Mechanistic Interpretability Circuits in Language Models

Jul 8, 2026cs.LG

Distributed Sparse Interventions in Language Models

Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and select among competing tasks. To study the role of model components in task behaviour, their causal influence can be investigated through interventions. Prior work on model steering has largely focused on interventions along global directions in activation space, modeling task representations as approximately linear and additive. By studying interventions at the neuron level, we find substantial, neuron-specific nonlinear effects on model outputs that are not captured by current steering approaches. We introduce Distributed Sparse Interventions (DSI), an intervention approach that considers nonlinearities and interactions between neurons across layers to identify sparse sets of neurons that elicit task-relevant computations. Across a range of tasks, we demonstrate that DSI can activate task behaviour in instruction-tuned language models by localising and intervening on as few as 0.01% of neurons, highlighting the effectiveness of sparse, distributed interventions in the neuron basis. Additionally, adopting a set-based perspective enables computations over the identified neuron sets, offering insights into the roles of individual neurons by analysing their effects across tasks. Through sparse interventions, DSI enables fine-grained control over model behaviour, localisation of task-relevant neuron sets, and furthers our understanding of task composition.

Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1

Max Planck School of Cognition · Center for Lifespan Psychology Max Planck Institute for Human Development · Machine Learning Group Technische Universität Berlin +5

Language Model Steering LLM Interpretability Circuits in Language Models Causal Interventions in Language Models

Jul 2, 2026cs.LG

Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior. However, self-repair creates a blind spot: ablating a primary component can activate a dormant backup, so a circuit that explains behavior in the intact model can become incomplete under the intervention used to test it. We formulate this gap as conditional circuit completion: given a primary set, identify components that become causally important after its removal. We introduce conditional co-ablation (CoAx), which ranks candidates by growth in ablation effect after primary-set removal. We show that a perfectly dormant backup can be indistinguishable from an irrelevant component to per-unit intact-state scores, whereas its conditional effect change exactly aggregates all interaction orders linking it to the removed set. On GPT-2-small's Indirect Object Identification (IOI) circuit, CoAx recovers the documented backup heads at 0.941 ROC-AUC, versus 0.815 for the strongest intact-state attribution baseline and 0.758 for the matched conditional-energy control. Recovery drops to 0.40 +/- 0.13 AUC for alternative component sets matched in behavioral effect, output displacement, and depth, showing that recovery is specific to the removed circuit. Beyond recovery, the CoAx-selected heads are causally load-bearing: freezing them after primary removal sharply reduces the IOI margin, while adding them to the incomplete circuit reduces incompleteness from 0.75 to 0.21. More broadly, conditional growth aligns with intervention-derived repair in 11/12 held-out instances across 4 mechanism clusters, and CoAx completions outperform matched random completions on all 8 non-GPT-2 models spanning 6 architecture families. Together, causal explanations of self-repairing transformers must account for backup circuitry when primary components fail.

Zhiren Gong, He Lu, Tiantong Wang +6

College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Causal Interventions in Language Models

Jun 23, 2026cs.AI

Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize. In this work, we study whether language model (LM) agents can assist with this explanation problem once a circuit has already been identified. We introduce AgenticInterpBench, a benchmark for circuit explanation built from 84 semi-synthetic transformer circuits with 163 component-level annotations. We propose HyVE (Hypothesize, Validate, Explain), an agentic explainer that analyzes each component through an iterative loop of observation, hypothesis generation, and causal validation, eventually producing a component-level explanation and a circuit-level task description. Across four LM backbones, HyVE recovers useful component- and task-level explanations, but no backbone is uniformly best. Our analysis shows that strong backbones usually form observation-grounded hypotheses, while failures more often arise later in the validation loop, through incomplete validation plans, code execution errors, or unresolved hypotheses. A case study on an arithmetic circuit in Llama-3-8B shows that the same formulation can extend beyond semi-synthetic benchmarks to naturally trained models. Overall, LM agents are promising circuit explainers, but reliable validation remains the key obstacle.

Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2

George Mason University · The Ohio State University

LLM Agent Evaluation Mechanistic Interpretability Circuits in Language Models Explainability Evaluation

Jun 21, 2026cs.CL

First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers

Why do multilingual language models sometimes generate in the wrong language, and why is this so hard to fix? We introduce Language Identity Head Ablation (LIHA), a causal intervention that zeros each attention head individually and measures the resulting language switch rate across a parallel dataset of 2,700 prompt-language pairs spanning seven languages. Applied to GPT-2, LIHA identifies a small set of first-token broadcaster heads - led by L6H1 (switch rate 0.32, 3.23

σ

above the population mean) - that attend persistently to the first prompt token, propagating its language signal throughout generation. Compensatory redistribution when heads are ablated is statistically significant (p <

10^{-5}

) and follows a directional, hierarchical pattern: compensation always recruits heads in layers above the ablated head, suggesting a feedforward cascade rather than global diffusion. To probe how training regime shapes these circuits, we apply LIHA to a controlled pair - Qwen2.5-1.5B-Base and Qwen2.5-1.5B-Instruct - identical in architecture and size, differing only in training. The base model is nearly flat (max SR=0.016, 200/336 heads at SR=0.0); the instruct model concentrates causal influence sharply at layer 0, led by L0H5 (SR=0.224, 8.93

σ

above mean), with all other layers near zero. This controlled comparison provides direct causal evidence that instruction tuning reorganizes language identity circuits toward early-layer localization. Extended experiments with Chinese and Russian confirm that first-token broadcasting is script-specific in GPT-2, with non-Latin languages handled at layer 0 - the same locus as the instruction-tuned model. Code and data will be released upon publication.

Arjun Pillai, Christian Hoang, Anjelo Jann Laroza

1Irvington High School · 2GenAI4E · 3Mapua University

Multilingual Language Models LLM Interpretability LLM Fine-Tuning Circuits in Language Models Causal Interventions in Language Models Language Model Robustness

Jun 15, 2026cs.LG

Scalable Circuit Learning for Interpreting Large Language Models

A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but their high dimensionality makes existing intervention-based circuit learning methods computationally prohibitive. We propose CircuitLasso, a scalable circuit-learning approach based on sparse linear regression. CircuitLasso recovers circuits whose structural accuracy matches that of state-of-the-art intervention-based methods on the benchmark data, at a fraction of the computational cost. For interpretability, CircuitLasso efficiently uncovers relationships among SAE features, showing how human-interpretable semantic features propagate through the model and influence its predictions. Finally, we validate the utility of our learned circuits by leveraging their insights to achieve comparable performance at substantially lower cost on a domain-generalization task.

Naiyu Yin, Dennis Wei, Tian Gao +3

Lehigh University, Mathematics Department, Bethlehem, USA · IBM Research, Yorktown Heights, USA.

Circuit Discovery LLM Interpretability Mechanistic Interpretability Circuits in Language Models

Jun 15, 2026cs.LG

Demystifying Variance in Circuit Discovery of LLMs

Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task. Although the current state-of-the-art method (EAP-IG) performs well on the metric of (un)faithfulness, it suffers from substantial variability. This includes resampling variance, where the circuit changes when we probe with a new batch of data from the same distribution; rephrasing variance, where the discovered circuit shifts when the prompts are rephrased; and sample-wise variance, where a circuit with low population unfaithfulness exhibits large fluctuations in unfaithfulness across individual samples. This paper studies the roots of these variances. We demonstrate that CEAP, our new circuit discovery method that improves upon EAP-IG with a theoretical guarantee, can substantially lessen resampling variance. We further show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model. This leads us to argue that it may be challenging to find a comprehensive circuit that explains and controls the model's behavior on a task, which can be expressed in countless templates, suggesting that LLMs may be inherently hard to steer. We show that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem. Regarding sample-wise variance, we argue that it is largely benign: extremely poor unfaithfulness scores often stem from how unfaithfulness is defined, rather than from defects in the measured circuits. We show that the magnitude of unfaithfulness is affected by selective contribution scaling, a neural mechanism that accounts for the extremely poor scores sometimes observed.

Frank Zhengqing Wu, Francesco Tonin, Volkan Cevher

Laboratory for Information and Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Laboratory for Informationand Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

Prompt Sensitivity Circuit Discovery LLM Interpretability Mechanistic Interpretability Explanation Stability Circuits in Language Models

Jun 11, 2026cs.CL

Localizing Anchoring Pathways in Language Models

Irrelevant numbers in a prompt can shift language model judgments, producing anchoring effects in numerical reasoning. We study where this anchor-sensitive signal is carried inside language models using a controlled multiple-choice setup with shared answer options. We define a logit-difference metric comparing the correct answer option with the answer option corresponding to the anchor, and validate that it tracks behavioral anchoring. Using attribution-based circuit localization on 7B--8B Qwen and Llama base and instruction-tuned models, we find that edge-level methods recover this signal more faithfully than node-level methods. Low- and high-anchor circuits transfer strongly within a model, suggesting shared pathway structure across anchor direction. However, sparse transfer across base and instruction-tuned variants is less reliable, indicating that post-training changes which pathways matter most. Overall, our results provide a mechanistic account of how anchoring-related decision signals are carried inside language models.

Hillary N. Owusu, Sarah Wiegreffe, Naomi H. Feldman

University of Maryland, College Park

Numerical Reasoning in Language Models LLM Interpretability Circuits in Language Models

Jun 5, 2026cs.LG

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these importance estimates serve as the evidence for identifying circuits, systematic errors can lead to the misidentification of the underlying mechanisms. While activation patching provides a gold-standard causal metric, its computational cost is prohibitive at scale. Practitioners instead rely on attribution patching, a gradient-based, first-order approximation whose reliability remains poorly understood. In this work, we characterize the source of this unreliability, demonstrating that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component. This insight yields three practical tools: (i) a reliability score to detect untrustworthy estimates, (ii) error bounds quantifying potential attribution mis-specifications, and (iii) a Hessian-vector-product (HVP) correction that eliminates the leading-order error with only one additional backward pass. In evaluations across five model families (124M-9B parameters) and both random-token and naturalistic (name-swap) perturbations, HVP is the only second-order correction feasible at larger scale, where standard baselines like Integrated Gradients become computationally prohibitive. In comparative experiments, a multi-step HVP variant matches or exceeds the accuracy of Integrated Gradients at significantly lower compute, outperforming prior second-order baselines. These improvements lead to higher-fidelity circuit recovery on standard benchmarks and support a Screen-Flag-Fix workflow that targets computational effort only toward the components flagged as unreliable.

Luyang Zhang, Jialu Wang

1Carnegie Mellon University · University of California, Santa Cruz

Gradient-Based Attribution LLM Interpretability Causal Attribution Mechanistic Interpretability Circuits in Language Models Activation Patching

Jun 3, 2026cs.LG

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families. The recipe ports across pipelines; the specific circuit it identifies does not. Across four composed tasks (indirect-object identification, greater-than, successor sequences, variable binding) and three 1B-class language models from distinct training pipelines (Pythia 1B / Pile / dense; OLMo 1B / DCLM / dense; OLMoE 1B-7B / DCLM / mixture-of-experts), we run a unified protocol with the matched-random null sampled across ten seeds per cell. The resulting 12 (task, model) cells contain no two that share the same primary causal screen at comparable effect size: the same task, with the same behavioral capability, is implemented through different attention-pattern types across models. We introduce a five-category screen-outcome taxonomy -- primary cause, secondary cause, correlate, interferer, null -- with quantitative thresholds, and show that all five outcomes appear in the panel. We propose a falsifiable hypothesis: the MoE model in our panel builds composed-task circuits on top of a foundational previous-token positional substrate (the prev-token-circuit ablation is the strongest causal screen on 3 of 4 tasks for OLMoE 1B-7B), with the IOI exception consistent with IOI being a final-position name-copying task whose structure directly probes a different pattern. The hypothesis comes with explicit predictions for other MoE language models. We frame the methodology honestly: the spectral participation-ratio signal from the companion methodology paper is a general indicator of specialized computation; what makes a finding task-specific is the task-pattern screen plus a per-model causal verification.

Yongzhong Xu

Attention Head Analysis Decoder-Only Language Models LLM Interpretability Circuits in Language Models Causal Interventions in Language Models Language Model Probing

May 25, 2026cs.AI

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual decision process. Existing CoT unfaithfulness detectors mainly rely on external signals from generated rationales, such as textual plausibility or answer consistency, while overlooking evidence from the model's internal computation. Although recent circuit tracing methods provide a way to obtain model-internal evidence by tracing how information flows through model components during reasoning, constructing full reasoning circuits for long CoTs is costly and difficult to scale. To address these challenges, we propose Circuit-guided Internal-External Discrepancy Scorer (CIE-Scorer), a framework for instance-level CoT unfaithfulness detection. The key idea is that faithful reasoning traces should align with the model's computational process, whereas unfaithful traces may diverge from it. CIE-Scorer efficiently traces compact sentence-level circuits from informative reasoning tokens, constructs internal and external reasoning graphs, and measures their discrepancy using Fused Gromov--Wasserstein distance. Experiments on four datasets from FaithCoT-Bench show that CIE-Scorer achieves state-of-the-art performance while reducing the cost of circuit construction, demonstrating the effectiveness of combining mechanistic interpretability signals with external reasoning traces for CoT unfaithfulness detection.

Xu Shen, Zhen Tan, Song Wang +4

1Jilin University · University of Central Florida · 3Arizona State University +2

CoT Faithfulness LLM Auditing Circuits in Language Models Reasoning Trace Analysis

May 23, 2026cs.CL

CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer

A sparse 8-layer code transformer develops dedicated neural circuitry for every Python construct tested, and that circuitry is organised by a clean computational principle rather than by semantic category. We extract neural circuits for 106 concepts (43 AST node types, 63 builtin objects) by marginalising across 63,800 controlled prompts, and decompose each circuit into concept-specific and token-driven components using contrastive checker prompts that present a keyword token without its associated syntactic structure. Three findings emerge. First, all 106 concepts produce non-empty universal circuits at every one of nine parameter settings, and the ranking of concept-specificity across constructs is stable across the sweep - survival is not an artifact of a permissive threshold. Second, AST circuits contain a genuine concept component distinct from token activation: concept-only neurons constitute up to 62.5% of the loudest-firing neurons at mid-to-late layers, while builtin circuits are almost entirely token-driven. Third, six computationally atomic constructs - Import, ImportFrom, Break, Continue, Pass, Assert - cluster together despite being semantically unrelated, sharing only the property of being single-statement constructs requiring no nested body; this atomicity super-cluster, together with a four-tier hierarchy organised by token ambiguity and structural distinctiveness, shows that the model's internal organisation tracks computational structure rather than meaning. The methodology, full decomposition data, and analysis code are released.

Piotr Wilam

University College London

Transformer Interpretability Circuit Discovery Mechanistic Interpretability Circuits in Language Models Code Language Models

May 21, 2026cs.LG

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?

Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities. Recent work has shown that reinforcement learning (RL) retains prior capabilities more effectively than supervised fine-tuning (SFT), attributing this to policy-gradient updates remaining closer to the base policy \cite{shenfeld2025rl}. We extend this behavioral account to the mechanistic level and ask whether RL's advantage is mirrored by stronger preservation of internal computational circuits. We introduce differential circuit vulnerability, a head-level measure of how much a circuit degrades under fine-tuning, and use it to compare RL and SFT on Qwen2.5-3B-Instruct adapted to scientific question-answering. We find a clear mechanistic trade-off: SFT adapts more rapidly to the target task but produces substantially greater circuit disruption and forgetting of prior capabilities, whereas RL preserves a larger fraction of the base circuit at the cost of slower task adaptation. These findings suggest that circuit preservation may help explain why RL is more robust to catastrophic forgetting. We released our code here: https://github.com/rl-sft-circuit-research/differential-circuit-vulnerability.

Jeanmely Rojas Nunez, Viraj Sawant, Nathan Allen +4

Algoverse AI Research · Independent

Supervised Fine-Tuning Mechanistic Interpretability Circuits in Language Models RL Fine-Tuning Catastrophic Forgetting

May 18, 2026cs.CL

Language-Switching Triggers Take a Latent Detour Through Language Models

Backdoor attacks on language models pose a growing security concern, yet the internal mechanisms by which a trigger sequence hijacks model computations remain poorly understood. We identify a circuit underlying a language-switching backdoor in an 8B-parameter autoregressive language model, where a three-word Latin trigger (nine tokens) redirects English output to French. We decompose the circuit into three phases: (1) distributed attention heads at early layers compose the trigger tokens into the last sequence position; (2) the resulting signal propagates through mid-layers in a subspace orthogonal to the model's natural language-identity direction; (3) the MLP at the final layer converts this latent signal into French logits. The entire circuit flows through a serial bottleneck at a single position: corrupting that position at any layer entirely mitigates the trigger but also hinders the model's capabilities. The orthogonal latent encoding suggests that defenses that search for language-like signals in intermediate representations would miss this trigger entirely.

Francis Kulumba, Wissam Antoun, Théo Lasnier +2

1Inria Paris · 2Sorbonne Université

LLM Backdoor Attacks Mechanistic Interpretability Circuits in Language Models

May 12, 2026cs.CL

All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs

In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional Anisotropy Hypothesis: the idea that functions in large language models (LLMs) are localised to a unique or near-unique internal mechanism. We show that a single LLM task can instead be supported by multiple, structurally distinct circuits or sheaves that are simultaneously faithful, sparse, and complete. To systematically uncover such competing mechanisms, we introduce Overlap-Aware Sheaf Repulsion, a method that augments the CSD objective with an explicit penalty on structural overlap across multiple discovery runs, enabling the discovery of circuits or sheaves with strong task performance but minimal shared structure across a plethora of common CSD benchmarks. We find that this phenomenon becomes increasingly pronounced as the number of discovered sheaves grows and persists robustly across major CSD methods. We further identify an ultra-sparse three-edge sheaf and show that none of its edges is individually indispensable, undermining even weakened notions of canonical or essential components. To explain these findings, we propose a Distributive Dense Circuit Hypothesis and provide a theoretical analysis demonstrating that non-unique, low-overlap circuit explanations arise naturally from high-dimensional superposition under mild assumptions. Together, our results suggest that mechanistic explanations in LLMs are inherently non-canonical and call for a rethinking of how CSD results should be interpreted and evaluated.

Xi Chen, Mingyu Jin, Jingcheng Niu +7

University of Toronto · The Hong Kong University of Science and Technology (Guangzhou) · Rutgers University +2

Circuit Discovery LLM Interpretability Circuits in Language Models

May 9, 2026cs.AI

Data-driven Circuit Discovery for Interpretability of Language Models

Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are hypothesis-driven; they first informally define a task with a dataset, and then apply a circuit discovery algorithm over that dataset to obtain a single circuit. This imposes two strong assumptions: that the LM implements the task with a single circuit, and that the dataset adequately represents the task as humans understand it. We systematically test these assumptions across four previously studied tasks and find that even minor dataset variations that preserve task semantics can produce circuits with low edge overlap and cross-dataset faithfulness. More strikingly, when applied to a mixed dataset with two distinct tasks whose separately discovered circuits have near-zero cross-faithfulness, existing methods still return a single circuit with high faithfulness across both tasks. This indicates that current methods discover dataset-specific circuits, rather than general task circuits. We propose Data-driven Circuit Discovery (DCD), a new discovery framework that drops both assumptions: instead of returning a single circuit for a dataset, DCD first clusters examples in the dataset by how similarly the model processes them and discovers a separate circuit for each group. This allows distinct mechanisms to appear separately rather than merged into a single circuit; each circuit explains its group, not the full task. Experiments show that DCD discovers multiple circuits per dataset, each more faithful to its group than a single circuit discovered by existing methods. Broadly, DCD lets the data reveal mechanistic structure within LMs, rather than relying on human-defined task boundaries that may not align with how models organize their computation.

Daking Rai, Mor Geva, Ziyu Yao

George Mason University · Tel Aviv University

Circuit Discovery LLM Interpretability Circuits in Language Models

May 9, 2026cs.CL

Architecture, Not Scale: Circuit Localization in Large Language Models

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia and Qwen2.5, we find that grouped query attention produces circuits that are far more concentrated and mechanistically stable than standard multi-head attention at comparable scales. The same concentration pattern holds across indirect object identification, induction heads, and factual recall. Within a single architecture family (Qwen2.5), factual recall circuits undergo a discrete phase transition above a critical scale, collapsing to a single bottleneck rather than degrading gradually. These findings suggest that some architectural choices make large models more tractable to study and that interpretability difficulty is not a fixed consequence of model size.

Sohan Venkatesh

Manipal Institute of Technology Bengaluru.

Transformer Interpretability Grouped-Query Attention Circuit Discovery Attention Head Analysis Mechanistic Interpretability Circuits in Language Models

May 8, 2026cs.CL

How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits

The circuits framework in mechanistic interpretability aims to identify sparse subgraphs of model components that are causally responsible for a behavior, typically evaluated by measuring necessity and sufficiency. But these criteria say little about whether a circuit consistently captures how a model performs a task, or if it is specific to that task. We study these two properties, consistency and specificity, across six tasks and five models, extracting circuits at the component level (attention heads and MLP blocks) and at the level of individual MLP neurons. We find that component-level circuits are highly consistent and causally important for most tasks, but they are not specific: for a given task, ablating its own circuit drops accuracy by about as much as ablating another task's circuit. Neuron-level circuits, on the other hand, exhibit higher specificity across tasks, but far less consistency within tasks. This is explained by circuit overlap: component-level circuits share most of their components across tasks, related or not, while neuron-level circuits overlap only between closely related tasks. In a case study of the components shared by the task circuits of Llama-3.2-3B, we show that they consist mostly of MLP blocks, while the few attention heads within turn out to have general-purpose roles. Overall, our findings raise questions about the degree to which circuits can support targeted understanding of, and intervention on, model behavior.

Michael Li, Nishant Subramani

Northeastern University · Carnegie Mellon University – Language Technologies Institute

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Causal Interventions in Language Models