arXiv AI September 2, 2026 By Wendy Zheng, Yinhan He, Liang Wu, Jundong Li

S^3martCirc: Self-supervised Smart Circuit Discovery

S^3martCirc is a self‑supervised framework that jointly discovers and interprets neural circuits in large language models, rather than treating circuit discovery and functional interpretation as separate stages. It abstracts node behavior into two general computational roles that generalize across tasks and introduces a quantitative metric for assigning these roles, enabling simultaneous identification of importance and function. Experiments demonstrate that S^3martCirc outperforms existing methods in circuit discovery.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 24

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

arXiv:2606. 24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize.

By Ayan Antik Khan, Harsh Kohli, Yuekun Yao, Huan Sun, Ziyu Yao

llms agents benchmarks safety

arXiv Machine Learning

Jul 2

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

arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.

By Hussein Chouman, Wataru Sasaki, Tomokazu Matsui, Hirohiko Suwa, Keiichi Yasumoto

llms safety

arXiv Machine Learning

Jul 9

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

arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.

By Pranav Sawant, Jakub Krej\v{c}\'i

llms safety

arXiv AI

Aug 3

Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL

arXiv:2603. 09161v2 Announce Type: replace-cross Abstract: Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by Intellectual Property (IP) and costly to annotate.

By Siyang Cai, Cangyuan Li, Haoyu Gao, Kun Wang, Yinhe Han, Ying Wang

llms benchmarks

arXiv Machine Learning

Jun 2

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation

arXiv:2505. 17630v4 Announce Type: replace-cross Abstract: Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis.

By Joakim Edin, Casper L. Christensen, R\'obert Csord\'as, Tuukka Ruotsalo, Zhengxuan Wu, Maria Maistro, Jing Huang, Lars Maal{\o}e

llms benchmarks safety

arXiv AI

Jun 16

Scalable Circuit Learning for Interpreting Large Language Models

arXiv:2606. 16939v1 Announce Type: cross Abstract: A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior.

By Naiyu Yin, Dennis Wei, Tian Gao, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Yue Yu

llms benchmarks safety

One email a morning, machine-written

Related stories

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

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

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

Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation

Scalable Circuit Learning for Interpreting Large Language Models