method · first seen 7 Oct 2026
circuit discovery
Also: mechanistic interpretability circuits
Identifying small interpretable subnetworks that implement specific subtasks inside a neural network.
Mentions per week
PapersCodeDiscussion
Earliest sources
- CircuitTree: Composing Circuits into A Syllable TranscriberPapers · 7 Oct 2026 · Jiankun Wei, Ewan Dunbar, Gerald Penn
- Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks LocalisedPapers · 14 Oct 2026 · Harsh Kumar, Tanmay Shailesh Joshi, Rahul Maity, Anusa Saha
- Are Linguistic and Arithmetic Circuits Dissociated in LLMs?Papers · 20 Oct 2026 · Riku Kisako, Tatsuki Kuribayashi, Ryohei Sasano
- Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discoveryPapers · 23 Oct 2026 · Marek Masiak, Andrzej Szablewski, Nicola Cancedda, Constantin Venhoff
- Understanding AI from the Inside: The State of Mechanistic Interpretability for AI SafetyPapers · 5 Nov 2026 · Fazl Barez, Tung-Yu Wu, Hunar Batra, Gabriele Dominici, Florent Draye, Yanai Ela…
Latest sources
- Understanding AI from the Inside: The State of Mechanistic Interpretability for AI SafetyPapers · 5 Nov 2026 · Fazl Barez, Tung-Yu Wu, Hunar Batra, Gabriele Dominici, Florent Draye, Yanai Ela…
- Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discoveryPapers · 23 Oct 2026 · Marek Masiak, Andrzej Szablewski, Nicola Cancedda, Constantin Venhoff
- Are Linguistic and Arithmetic Circuits Dissociated in LLMs?Papers · 20 Oct 2026 · Riku Kisako, Tatsuki Kuribayashi, Ryohei Sasano
- Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks LocalisedPapers · 14 Oct 2026 · Harsh Kumar, Tanmay Shailesh Joshi, Rahul Maity, Anusa Saha
- CircuitTree: Composing Circuits into A Syllable TranscriberPapers · 7 Oct 2026 · Jiankun Wei, Ewan Dunbar, Gerald Penn