method · first seen 4 Oct 2026
circuit analysis
Also: mech interp, interpretability, mechanistic learning, feature decomposition, mechanistic interpretability, interpretability of transformers
Identifying sparse subgraphs of a neural network that implement specific behaviors.
Mechanistic interpretability, including circuit analysis, tries to explain neural network behavior by locating the internal features, neurons and sparse subgraphs that carry out specific computations. The sources here apply long-standing tools to new settings rather than introducing the idea. Papers study suppressed safety features, carry propagation in small multiplication transformers, uncertainty quantification, an astronomy foundation model, and web-agent hallucination. Others question the method itself, for example how to separate steering effects from actual mechanism and what logic of inference supports mechanistic claims. On the code side, there are hobbyist repos for neuron steering and exploring Qwen models, plus a Hacker News discussion of using an LLM to interpret model weights.
The field has been an active research area since roughly 2020, so this burst reflects steady output rather than a new idea. The points worth watching are its spread into scientific foundation models and agents, and the growing attention to whether interpretability findings are causally valid.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 81 on 14 Nov 2026 · 58 mentions in 28 days · 57 independent groups · papers → discussion → code · first seen 6 weeks ago · acceleration -0.71
Earliest sources
- A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNsPapers · 4 Oct 2026 · Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite, Abhijeet Salunke
- Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation PotentialPapers · 4 Oct 2026 · Swadesh Swain, Sanghamitra Dutta
- Separators Make Carry Propagation Learnable:The Geometry of Latent Carry in a Multiplication TransformerPapers · 5 Oct 2026 · Sama Satariyan, Raphael Cousin, G{é}rard Biau
- Does the Model Use the Feature? Separating Steering from Mechanism in LLMsPapers · 5 Oct 2026 · Tong Che, Yilong Li
- Mechanistic Interpretability of Atmospheric Rivers in GraphCastPapers · 6 Oct 2026 · Madelyn Mathai, Timothy B. Higgins, Kevin M. Grise, Chirag Agarwal, Antonios Mam…
- Matching Object or Relation? Tracing Abstract Reasoning Inside VLMsPapers · 6 Oct 2026 · Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
Latest sources
- ShutongLiang/Neural-State-OSCode · 14 Nov 2026 · ShutongLiang · 84 stars
- Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element HallucinationPapers · 13 Nov 2026 · Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao
- Tracing Knowledge and Reasoning in LLMPapers · 12 Nov 2026 · Yang Wang, Xiao Wang, Yiqi Liu, Chenghao Xiao, Eleni Vasilaki, Goran Nenadic, Ch…
- Where Is Uncertainty Observed? A Mechanistic Understanding of Uncertainty Quantification in LLMsPapers · 11 Nov 2026 · Xiaoyu Liang, Virginia Ceccatelli, Aliai Eusebi, Tobias Braun, Nils Loose, Carlo…
- A Mechanistic Interpretability Study of an Astronomy Foundation ModelPapers · 11 Nov 2026 · Rachel C. Zhang, Alberto Bietti, Wes Gurnee, Alessandro Favero, Miles Cranmer
- Mechanistic Interpretability Needs a Logic of InferencePapers · 10 Nov 2026 · Zhimin Hu, Chen Jiang, Hanbo Xie, N. Apurva Ratan Murty, Sashank Varma
- Mechanistic Interpretability of Deep Neural Networks: Methods, Frameworks, and PerspectivesPapers · 10 Nov 2026 · Lorenzo Cirillo, Irene Amerini, Andrea Cavallaro
- MicroLens: Read, Trace, and Rewire the Residual Stream with Two LensesPapers · 9 Nov 2026 · Nika Zahedi, Fangyi Zhu, Anna Wu
- A Geometric Invariant of Attention Predicts Head Specialization from Weights AlonePapers · 9 Nov 2026 · Miguel P. Bento
- Miyamoto-Renya/LaplacesScissorsCode · 7 Nov 2026 · Miyamoto-Renya · 32 stars
- Can small transformers learn the language of Coxeter groups?Papers · 7 Nov 2026 · J. Elisenda Grigsby, Yiyao Huang, Arushi Katyal, Ryan Lin, Pranav Ramakrishnan,…
- Detecting and Explaining Robot Policy Failures from Sparse Internal FeaturesPapers · 7 Nov 2026 · Riad Ahmed, Sujosh Nag, Moniruzzaman Akash, Momotaz Begum