Mechanistic Interpretability

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-14

10 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

13 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Inside this field

Focused directions

Focused topic

Model Interpretability

Within Mechanistic Interpretability

269 papersExplore

Focused topic

Mechanistic Interpretability

Within Mechanistic Interpretability

158 papersExplore

Focused topic

Interpretable Models

Within Mechanistic Interpretability

38 papersExplore

434 papers

Latest in Mechanistic Interpretability

Browse all topics →

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
May 25, 2026Barsat KhadkaMechanistic Interpretability Circuits
Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
May 25, 2026Taeseong Yoon, Heeyoung KimLarge Language Model Uncertainty Model Interpretability
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
May 25, 2026Xu Shen, Zhen Tan, Song Wang +4Reasoning Traces Explanation Faithfulness
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
May 25, 2026Aditya SridharConcept Bottleneck Models Model Interpretability
Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability
May 24, 2026David N. Olivieri, Antonio F. Pérez RodríguezAutoregressive Transformers Mechanistic Interpretability
Interpretability Transfer from Language to Vision via Sparse Autoencoders
May 24, 2026Alexey Kravets, Da Li, Chuan Li +2Large Vision Language Models Improving Sparse Autoencoders
Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes
May 24, 2026Mini Han Wang, Liting Huang, Wei Hong +1Interpretable Diabetic Retinopathy Grading Hypoglycemia Classification
The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
May 24, 2026James HenryTransformer Architectures Model Activations
Building Better Activation Oracles
May 23, 2026Jan Bauer, Celeste De Schamphelaere, Adam Karvonen +2Model Activations Model Interpretability
Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m
May 23, 2026Jordan F. McCannTransformer Architectures Transformer Layers
Learning dynamical systems with biochemically informed neural ordinary differential equations
May 22, 2026Luis L. Fonseca, Reinhard C. Laubenbacher, Lucas BöttcherNeural Ordinary Differential Equations Dynamical Systems
Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
May 22, 2026Willem Diepeveen, Deanna NeedellData-Driven Model Interpretability
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
May 22, 2026Po-Kai Chen, Niki van Stein, Aske PlaatTransformer Attention Transformer Architectures
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
May 21, 2026Maryia Zhyrko, Daisy Monika Lal, Erik van Mulligen +1Mental Health Psychology
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
May 21, 2026Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel +3Multilingual Mechanistic Interpretability
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
May 21, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuSparse Autoencoder Features Semantic Representations
The Neglected Baseline in Model Interpretation
May 21, 2026Yongjin Cui, Xiaohui FanInterpretable Models Wireless Foundation Models
Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
May 21, 2026Xianhao Song, Yuang Zhang, Yuqi She +2Time-Series Classification Time Series
Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
May 21, 2026Neel SomaniTransformer Architectures Model Interpretability
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
May 21, 2026Sungjun Lim, Heedong Kim, Andrew Lee +1Model Interpretability Mechanistic Interpretability
Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
May 20, 2026Jacek Karolczak, Jerzy StefanowskiFeature Importance Explainability
HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation
May 20, 2026Shreyas Vinaya Sathyanarayana, Raja Sekhar Pappala, Deepak WarrierSequential Recommendation Model Interpretability
Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy
May 20, 2026Lawhori Chakrabarti, Jennifer Johnson-Leung, Bert Baumgaertner +3Transformer Encoder Metaphors
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
May 20, 2026Nura Aljaafari, Danilo S. Carvalho, Andre FreitasMechanistic Interpretability Circuits
SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
May 20, 2026Wanying Tan, Shuo Yan, Dazhi Huang +7Bacterial Colony Counting Model Interpretability
Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
May 20, 2026Romeo Valentin, Olivia Beyer Bruvik, Marc R. Schlichting +1Aerotrack Mechanistic Interpretability
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
May 19, 2026Julien Colin, Lore Goetschalckx, Nuria Oliver +1Model Interpretability Vision Foundation Models
INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
May 19, 2026Seongjun Lee, Seokhyun Lee, Changhee LeeTime-Series Classification Statistical Shape Model
Where Does Authorship Signal Emerge in Encoder-Based Language Models?
May 19, 2026Francis Kulumba, Guillaume Vimont, Laurent Romary +1Authorship Encoding Models
CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models
May 19, 2026Yike Sun, Mingkun Xu, Mu You +5Model Interpretability Efficient Influence Function
ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
May 19, 2026Hongjiang Chen, Xin Zheng, Pengfei Jiao +5Temporal Graph Neural Networks Model Interpretability
Mechanisms of Object Localization in Vision-Language Models
May 19, 2026Timothy Schaumlöffel, Martina G. Vilas, Gemma RoigPrecise Localization Localization Methods
A Family of Divergence Measures for Evaluating the Reconstruction Quality of Explainable Ensemble Trees
May 19, 2026Massimo Aria, Agostino Gnasso, Carmela IorioEnsemble Quantitative Idea Divergence
Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
May 18, 2026Manal Benhamza, Marianne Clausel, Myriam TamiCausal Representation Learning Identifiability
Are Sparse Autoencoder Benchmarks Reliable?
May 18, 2026David ChaninMasked Autoencoders Model Interpretability
iPOE: Interpretable Prompt Optimization via Explanations
May 18, 2026Jiahui Li, Yarik Menchaca Resendiz, Sean Papay +1Prompt Engineering Prompt Optimization
Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection
May 18, 2026Hang-Cheng Dong, Guodong Liu, Dong Ye +1Scalable Defect Detection Model Interpretability
Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space
May 18, 2026Alon Bebchuk, Nir ShavitLotteries Feature Space
Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models
May 17, 2026Urban Širca, Maryam Alimardani, Stefanos Zafeiriou +1Electroencephalography Foundation Models Wireless Foundation Models
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
May 17, 2026Guancheng Zhou, Yisi Luo, Zhengfu He +5Mechanistic Interpretability Model Interpretability
Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE
May 17, 2026Minjong CheonArtificial Intelligence Weather Models Mechanistic Interpretability
Employing Vision-Language Models for Face Image Quality Assessment
May 17, 2026Erdi Sarıtaş, Eren Onaran, Vitomir Štruc +1Image Quality Assessment Multimodal Evaluation
Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability
May 17, 2026Nisreen Albzour, Sarah S. LamNon-Small Cell Lung Cancer Vision Transformer
Diversified Residual Symbolic Regression
May 15, 2026Koki Ikeda, Masahiro Nomura, Ryoki HamanoSymbolic Regression Kernel Ridge Regression
When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
May 14, 2026ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe +3Mechanistic Interpretability Semantic Similarity Metrics
Evidential Reasoning Advances Interpretable Real-World Disease Screening
May 14, 2026Chenyu Lian, Hong-Yu Zhou, Jing QinScreening Evidential Learning
K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles
May 14, 2026Giulia Patanè, Alessandra Menafoglio, Alexander Krauth +4Antibody Image Clustering
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
May 14, 2026Tommaso Mencattini, Francesco Montagna, Francesco LocatelloSemantic Representations Mechanistic Interpretability
Exploring Geographic Relative Space in Large Language Models through Activation Patching
May 14, 2026Stef De Sabbata, Rahul Baiju, Stefano Mizzaro +1Large Language Mechanistic Interpretability
Exemplar Partitioning for Mechanistic Interpretability
May 14, 2026Jessica RumbelowModel Activations Mechanistic Interpretability
Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems
May 14, 2026Emilio Mastriani, Alessandro Costa, Federico Incardona +2Predictive Maintenance Model Interpretability
Towards Fine-Grained and Verifiable Concept Bottleneck Models
May 14, 2026Yingying Fang, Haijie Xu, Shuang Wu +2Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows
May 13, 2026Alvaro Lopez Pellicer, Plamen Angelov, Marwan Bukhari +3Multimodal Clinical Data Mediation
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
May 13, 2026Cristian Hinostroza, Rodrigo Toro Icarte, Christ Devia +4Large Language Model Performance Cosine Similarity
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
May 13, 2026William Lehn-Schiøler, Magnus Ruud Kjær, Rahul Thapa +10Electroencephalography Foundation Models Mechanistic Interpretability
XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
May 13, 2026Iakovos-Christos Zarkadis, Christos DouligerisIntrusion Detection Unmanned Aerial Vehicle Detection
Tracing Persona Vectors Through LLM Pretraining
May 13, 2026Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira +2Personality Large Language Model Safety
Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
May 13, 2026Nicola Debole, Andrea Passerini, Stefano Teso +2Concept Bottleneck Models Annotations
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
May 12, 2026Sanah Suri, Kieran Ringel, Maike SonnewaldClass-Incremental Concept Bottleneck Model Ocean
Mechanistic Interpretability of ASR models using Sparse Autoencoders
May 12, 2026Dan Pluth, Zachary Nicholas Houghton, Yu Zhou +1Llm-Based Automatic Speech Recognition Speech Encoder

May 25, 2026 · cs.LGJ/K move · Enter open · S save

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability

Barsat Khadka

School of Computing Sciences and Engineering The University of Southern Mississippi

Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it. Automated methods have made this search systematic, but each one starts afresh for every behaviour, and the effort spent finding one circuit does nothing for the next. Circuit discovery has thus been automated, but not amortised. We ask whether circuit discovery can itself be learned. We frame it as a sequential decision problem over the computation graph of GPT-2 small, in which a policy removes edges until it reaches a compact subgraph that preserves the behaviour, guided by a faithfulness reward defined through causal intervention. A single policy trained across twelve behaviours recovers a faithful circuit for each, and once frozen it transfers to behaviours it never saw during training, recovering their known circuits without further search. A short warm-start improves these transferred circuits, returning far smaller ones than training from scratch. While the learned policy does not match a per-behaviour search on circuit size or cost, it shows that circuit discovery is a learnable, transferable procedure rather than a search repeated for every behaviour.

Mechanistic Interpretability Circuits Deep Reinforcement Learning Causal Intervention Heuristic Search Sequential Decision Making

Open paper Ask about it PDF