automated interpretability

Latest papers

10 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Nov 13, 2026

Interpretable weight-space programming builds transparent transformers and brain encoding models

Neural networks are powerful predictors, yet their opacity limits their usefulness in science, where the goal is explanation rather than mere prediction. In neuroscience, for example, deep encoding models accurately predict brain activity in response to natural stimuli, but struggle to reveal which stimulus features drive those predictions. Here we introduce interpretable weight-space programming (iWSP), a method in which an LLM agent iteratively builds interpretable models by explicitly programming their weights and features in code, without gradient-based training (backpropagation). Without backpropagation to tune parameters, the agent must draw on its prior knowledge and reason over previous trials to hypothesize, hand-craft, and refine human-interpretable computations mirroring the workflow of a human scientist. LLM audits confirm the interpretability of the hand-crafted models. We first validate iWSP by tasking it with constructing transformers for canonical benchmarks such as arithmetic and sentiment classification, finding that LLM agents can successfully craft compact, accurate networks directly. Next, we apply iWSP to build neural encoding models across vision, language, and audition. In the visual cortex, iWSP outpredicts existing interpretable baselines, uncovers distinct computations across early/higher visual areas, and generalizes to unseen data. In language fMRI, iWSP surfaces a confound in the data and in auditory ECoG, it systematically discovers interpretable acoustic features that predict neural activity. Together, these results establish iWSP as a general paradigm for aligning high predictive performance with human-interpretable scientific discovery.
Nov 13, 2026

DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process

Tools for interpreting the internal representations of Large Language Models (LLMs) increasingly rely on LLMs themselves to both generate and evaluate explanations, creating a self-referential automated interpretation process with minimal human oversight. This automation raises significant reliability concerns, which are exacerbated by the absence of ground truth. In practice, it is difficult to validate explanations or to attribute interpretability failures to their source -- whether they originate from the tool's extracted representations or from the LLM used in the process. To address these challenges, we present DECODE, a visual analytics system that reintroduces human oversight into the automated interpretation process. Our approach decomposes the diagnostic workflow into three progressive stages, isolating failure sources ranging from structural defects to explanation-level misalignments. Drawing inspiration from inter-coder consensus in qualitative analysis, we utilize consensus among independently generated explanations and their evaluation metrics as a proxy for reliability. To further scale human inspection, we employ a three-phase active seeding protocol that strategically recommends high-priority instances for manual review. Finally, we demonstrate the effectiveness of our approach through a case study on 16,384 Sparse Autoencoder features, showing that it can efficiently identify and attribute interpretability failures at scale.
Nov 8, 2026

The Shape of a Program: Path Signatures for Trace-to-Program Induction

Synthesizing programs from execution traces is a fundamental challenge in algorithmic interpretability and the reverse engineering of complex systems. We bring a rough-path-theoretic perspective to program induction, treating execution traces as high-dimensional rough paths and encoding them with the path signature transform, a tool from stochastic analysis whose expectation provably characterizes the distribution of traces a program induces. On three program-induction domains, Karel, List, and RASP, our log-signature trace encoder outperforms LSTM, Transformer, and Fourier baselines in almost every setting, with its largest margins when training data is scarce. We further observe that the trace-to-program pipeline is naturally contractive: it often produces valid programs that are shorter than the ground truth. We turn this into a bootstrapping procedure that exposes redundancy in the ground-truth supervision without any external oracle, which we demonstrate on redundancy-injected versions of our datasets. Finally, the log-signature encoder induces a markedly more interpretable latent geometry than the baselines, in which the nearest neighbors of every state lie on its own execution trace.
Oct 3, 2026

Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures

We develop a principled framework for constructing neural networks whose specific parameter realizations admit an explicit algorithmic interpretation. Existing algorithm-inspired architectures can explain the computational structure of a network, yet after standard training the learned parameters need not retain a clear relation to the motivating algorithm. We address this gap as follows. First, we model each data point as a sample of a class-dependent stochastic process and assume that statistics of this process can be estimated from a single sample and these statistics are sufficient to distinguish the classes. We then construct a neural network whose initial parameters exactly implement an algorithm for estimating these statistics, making the network fully interpretable. To account for mismatch between the idealized model and real data, we fine-tune this network while controlling its deviation from the algorithmic initialization. The trained network hence roughly retains the interpretation of the initial network. A PAC-Bayesian analysis yields a uniform generalization bound whose complexity term scales with the fine-tuning radius, providing a statistical motivation for our approach. We instantiate the framework for texture classification using the scattering transform to estimate the discriminative statistics.
Sep 27, 2026

Augmenting Visual Anomaly Detection with Automated Interpretability

Visual anomaly detectors identify deviations from known-normal data, but their anomaly signals may mix evidence of actual anomalies with benign visual variation. We investigate whether automated interpretability can augment visual anomaly detectors by identifying and intervening on different components of this signal. We decompose PatchCore nearest-normal residuals into sparse features using Sparse Autoencoders (SAEs), and provide high-activation and contrastive non-active examples to a Multimodal LLM, which describes each feature and labels it as anomaly, distractor, or uncertain. These labels guide interventions in the SAE hidden representation, where distractor features are suppressed and anomaly features amplified. The edited representation is then used to reconstruct patch embeddings, which are rescored with PatchCore. Across 40 categories from four benchmarks, applying both interventions jointly improves macro-average image-level AUROC from 0.8724 to 0.8857 on source data and from 0.8066 to 0.8210 under synthetic corruptions. On three additional RobustAD categories with real acquisition shifts, the same interventions improve AUROC from 0.8745 to 0.9056 on source data and from 0.6069 to 0.6599 under real acquisition shifts. Finally, individual feature interventions across all 43 categories show that the MLLM labels are aligned in aggregate with how features differently affect normal and anomalous images.
Aug 27, 2026

Efficient Auto-Interpretability of AI Models in Biology

Sparse autoencoders (SAEs), and other interpretability methods could turn AI models in Biology and other fields into engines of scientific discovery by explaining the superhuman capabilities of those models. However, a latent is only useful if we know three things: whether it is coherent, whether it can be described, and whether that description has predictive power. These questions are routinely conflated. We assemble them into a single pipeline and report the practical innovations each stage required. First, cross-seed dictionary stability prioritises which latents are worth spending resources to investigate. Second, an intruder-detection task asks whether a latents activating examples share a recognizable pattern. Third, a separate pass proposes a candidate biological description which we convert into falsifiable predictions which can be tested in silico. Deployed on the Boltz-1 Pairformer trunk, stability prioritisation finds interpretable latents using about 4.4 times fewer latent evaluations each, and at 5.2 times lower measured cost, while recovering over half of them, and the external check shows the surfaced motifs are significantly enriched for their claimed annotations. The results also suggest a possible tension: the cross- seed stability might be selecting for some types of features, like structure-related ones, much more than others, such as function-related features.
May 13, 2026

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features

Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability pipelines routinely assign each feature a short natural-language explanation. Existing critiques of this practice focus on polysemanticity -- one feature with many meanings -- or on whether explanations predict activations. We identify a complementary, structurally distinct problem we call descriptive collision: many distinct SAE features admit the same explanation. Reanalyzing the largest publicly-available dataset of human-annotated SAE features (Marks et al., 2025), comprising 722 annotated features across Gemma 2 2B and Pythia 70M, we find that the mean annotation string is reused across 3.07 features; 82.1% of features share their annotation with at least one other feature; and the single most common annotation string ("plural nouns") labels 101 distinct features spanning 18 layers and four model components. Information-theoretically, the average annotation resolves only 70% of feature identity. We formalize a property called discrimination, prove that current detection-style auto-interpretability scoring is invariant to collision, and propose two complementary corrective metrics -- collision-adjusted detection and discrimination scoring -- that explicitly penalize explanations that fail to distinguish a feature from its neighbors. The collision problem is independent of, and additive with, previously identified failure modes of auto-interpretability; ignoring it inflates reported feature interpretability by a quantity equal to roughly one-third of the bits required to identify a feature.
May 2, 2026

Automated Interpretability and Feature Discovery in Language Models with Agents

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an agent proposes competing hypotheses and iteratively tests them with targeted prompt controls and a multi-metric evaluation; and (2) feature discovery, where an agent generates prompt sets, constructs a k-nearest-neighbor graph in activation space, and retrieves candidate features using statistical separability and semantic coherence criteria. On Gemma-2 family models and MLP neurons in weight-sparse transformers, our agent improves over one-shot auto-interpretations, discovers language-specific and safety-relevant features, and produces auditable explanation traces, showing that agent-driven empirical loops yield sharper and more falsifiable explanations than one-shot labels.
Mar 20, 2026

Pitfalls in Evaluating Interpretability Agents

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of autonomy, ranging from fixed one-shot workflows to fully autonomous interpretability agents. This shift creates a corresponding need to scale evaluation approaches to keep pace with both the volume and complexity of generated explanations. We investigate this challenge in the context of automated circuit analysis -- explaining the roles of model components when performing specific tasks. To this end, we build an agentic system in which a research agent iteratively designs experiments and refines hypotheses. When evaluated against human expert explanations across six circuit analysis tasks in the literature, the system appears competitive. However, closer examination reveals several pitfalls of replication-based evaluation: human expert explanations can be subjective or incomplete, outcome-based comparisons obscure the research process, and LLM-based systems may reproduce published findings via memorization or informed guessing. To address some of these pitfalls, we propose an unsupervised intrinsic evaluation based on the functional interchangeability of model components. Our work demonstrates fundamental challenges in evaluating complex automated interpretability systems and reveals key limitations of replication-based evaluation.
Oct 22, 2025

Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments

Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image observations, performs SHAP-based feature attribution, and then employs RL-guided labeling to generate behaviorally consistent boundary datasets. Surrogate models, such as decision trees and regression-based functions, are subsequently trained to interpret RL policy's decision structure. We evaluate the proposed framework on two Atari environments using three deep RL algorithms and conduct human-subject study to assess the clarity and trustworthiness of the derived interpretable policy. Results show that our approach maintains competitive task performance while substantially improving transparency and human understanding of agent behavior. This work advances explainable RL by transforming SILVER into a scalable and behavior-aware framework for interpreting deep RL agents in high-dimensional, multi-action settings.