Mechanistic Interpretability

Ask about this topic

Recent momentum

-8%

11 papers in the last 28 days · 0.2% of indexed attention

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

Also in Mechanistic Interpretability

Neighbouring directions

Model InterpretabilityInterpretable Models

Weekly history

Recent digests

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

Period ending 2026-09-21

4 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

158 papers

Latest in Mechanistic Interpretability

Open your feed →
CardsList

  1. Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles

    Sep 17, 2026Noah Mamié, Laurin van den BerghRecommender SystemsProfile

  2. The Misery of Mechanistic Interpretability: A Formal Perspective

    Sep 14, 2026Tobias Ladner, Matthias AlthoffMechanistic InterpretabilityModel Interpretability

  3. Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)

    Sep 14, 2026Christian Fisch, Angela Altmeier, Martin Obschonka +2Artificial Intelligence SystemsMechanistic Interpretability

  4. What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

    Sep 14, 2026Lingheng Du, Yiming Tang, Xufeng Duan +1Sparse Autoencoder FeaturesMechanistic Interpretability

  5. On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing

    Sep 7, 2026Yuval Koren, Assaf Ben-Kish, Raja Giryes +2Dense Associative MemoryFactual Recall

  6. Large Language Models in Resolving Contextual Knowledge Conflicts

    Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1ConflictLarge Language Model Performance

  7. ObserverBench: Testing Mechanistic Estimates for Intervention and Control

    Sep 2, 2026Vijay ErramilliMechanistic InterpretabilityObservation

  8. S^3martCirc: Self-supervised Smart Circuit Discovery

    Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic InterpretabilityCircuits

  9. MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

    Aug 31, 2026Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5Model InterpretabilityMechanistic Interpretability

  10. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

    Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiNovel Jailbreak MethodJailbreaks

  11. RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons

    Aug 25, 2026Runyu Wang, Bo Liu, Xiaxin Zhang +6Neurophysiological CorrelatesMechanistic Interpretability

  12. Decoding Task Progress from VLA Representations

    Aug 13, 2026Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan +2Vision-Language-Action ModelsVisuomotor Policy

  13. Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

    Aug 13, 2026Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8DissociationDysarthric Speech

  14. Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

    Aug 12, 2026Mengru Wang, Junfeng Fang, Shuofei Qiao +16Artificial Intelligence SafetyArtificial Intelligence Scientists

  15. From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

    Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10Trustworthy Artificial IntelligenceModel Interpretability

  16. Measuring Semantic Abstractness of SAE Features via Nonlocality

    Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse Autoencoder FeaturesSemantic Representations

  17. Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

    Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic InterpretabilityModel Interpretability

  18. Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

    Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4Multilingual SafetyLarge Language Model Safety

  19. Finding Usable Weight Mechanisms with Tiled SVD

    Aug 7, 2026Ash Manvi, Samreena TajreenModel WeightsSingular Value Decomposition

  20. MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering

    Aug 6, 2026Jakub Poćwiardowski, Mateusz ModrzejewskiMusic GenerationConversational Music Recommendation

  21. Sparse Weight Decomposition for Efficient Circuit Extraction

    Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Model WeightsTransformer Architectures

  22. DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

    Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3Visual ReasoningMechanistic Interpretability

  23. Emergent Latent-State Computation under Stochastic Volatility

    Jul 28, 2026Xiaoyu Huang, Lulu WangIntermediate Latent StatesLatent States

  24. Do LLMs Know Their Vulnerable Scenarios?

    Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Large Language Model SafetyVulnerable Code

  25. Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation

    Jul 25, 2026Gonzalo A. RuzGene-Regulatory NetworksSurrogate Models

  26. Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

    Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head Self-AttentionLatent Representation

  27. Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry

    Jul 22, 2026Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm +1Atmospheric DynamicsWireless Foundation Models

  28. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiSemantic RepresentationsMechanistic Interpretability

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

    Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLarge Language Model PerformanceMechanistic Interpretability

  30. Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

    Jul 16, 2026Jihoon Hong, Julian Skifstad, Qiyue Dai +2Efficient World-Action ModelWorld Models

  31. Transcoders for Investigating Deception in Language Models

    Jul 16, 2026Darius Lim, Nathan Leow, Xin Wei ChiaDeceptionMechanistic Interpretability

  32. Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

    Jul 15, 2026Zachary IzzoMechanistic InterpretabilityTraining Data

  33. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Jul 14, 2026Ingmar Posner, Anson Lei, Bernhard SchölkopfScientific DiscoveryMechanistic Interpretability

  34. Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

    Jul 13, 2026Zixiang Xu, Sixian Li, Huaxing Liu +4JudgesGrading

  35. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    Jul 9, 2026Bendegúz Váradi, Zoltán KmettyImproving Sparse AutoencodersBert-Based Models

  36. Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

    Jul 9, 2026Amir AsiaeeModel InterpretabilityMechanistic Interpretability

  37. Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

    Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1Large Language Model JailbreaksLarge Language Model Performance

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

    Jul 8, 2026Pranav Sawant, Jakub KrejčíMechanistic InterpretabilityExplainable Artificial Intelligence

  39. Latent Programming Horizons in Coding Agents

    Jul 6, 2026André Silva, Han Tu, Martin MonperrusCoding AgentsMechanistic Interpretability

  40. Individual Parameters in Weight-Sparse Transformers Appear Interpretable

    Jul 3, 2026Arnau Marin-Llobet, Stefan HeimersheimMechanistic InterpretabilityModel Weights

  41. Towards Robustness against Typographic Attack with Training-free Concept Localization

    Jul 2, 2026Bohan Liu, Wenqian Ye, Guangzhi Xiong +3Frozen Contrastive Language-Image Pre-Training Visual EncoderVision Transformer

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

    Jul 2, 2026Zhiren Gong, He Lu, Tiantong Wang +6AblationMechanistic Interpretability

  43. Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

    Jul 2, 2026Rodrigo Mendoza-SmithImproving Sparse AutoencodersLarge Language Model Decoder

  44. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

    Jul 1, 2026Zihao Qi, Christopher EarlsQuantum Neural NetworksMany-Body Physics

  45. Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

    Jun 30, 2026Hussein Chouman, Wataru Sasaki, Tomokazu Matsui +2Mechanistic InterpretabilityModel Interpretability

  46. Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?

    Jun 30, 2026Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5Mechanistic InterpretabilityClosure

  47. Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies

    Jun 28, 2026Reza Habibi, Darian Lee, Magy Seif El-NasrTraining Data AttributionMechanistic Interpretability

  48. Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

    Jun 27, 2026David Courtis, Ting HuPersonalityMechanistic Interpretability

  49. Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

    Jun 26, 2026Sambaran BandyopadhyaySelf-AssessmentsIn-Context

  50. The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching

    Jun 25, 2026Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2Causal Mediation AnalysisMechanistic Interpretability

  51. PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding

    Jun 25, 2026Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts +3Protein Data BankProtein

  52. Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication

    Jun 25, 2026Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla +2BeesNon-Destructive Frying Oil Oxidation Assessment

  53. Radical AI Interpretability

    Jun 25, 2026Daniel A. Herrmann, Benjamin A. LevinsteinTrustworthy Artificial IntelligenceMechanistic Interpretability

  54. Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

    Jun 23, 2026Cosimo Galeone, Anna Ettorre, Minsu Park +2Mechanistic InterpretabilityModel Activations

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

    Jun 23, 2026Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2Mechanistic InterpretabilityCircuits

  56. AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent

    Jun 21, 2026Weidi Luo, Qiming Zhang, Yihao Quan +5Large Language Model SafetySafety

  57. Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs

    Jun 17, 2026Hyebin Cho, Suho Yoo, Jaehyuk Jang +2Large Audio Language ModelsConflict

  58. Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation

    Jun 17, 2026Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2Activation SteeringMusic Generation

  59. Effects of sparsity and superposition on loss in simple autoencoders

    Jun 16, 2026Mriganka Basu Roy Chowdhury, Eric McLaughlin WeinerImproving Sparse AutoencodersActivation Functions

  60. Scalable Circuit Learning for Interpreting Large Language Models

    Jun 15, 2026Naiyu Yin, Dennis Wei, Tian Gao +3Mechanistic InterpretabilityCircuits