Jacobian Lens – Qwen3.6-27B ｜ Neuronpedia

Revealing a Global Workspace in Language Models

Jacobian Lens – Qwen3.6-27B ｜ Neuronpedia © Neuronpedia 2026 Privacy & Terms Blog GitHub Slack Twitter Contact Neuronpedia Jacobian Lens NEW Natural Language Autoencoders NEW Assistant Axis NEW Circuit Tracer UPDATE Releases Jump To Search Steer SAE Evals Exports Guides API Community Blog Privacy & Terms Contact Sign In Jacobian Lens Gurnee et al. Tutorial Paper Video Qwen 3.6 27B Gemma 3 12B Other Models Tutorial 💬 Verbal Report 🤔 Directed Modulation 🕷️ Multi-Hop Reasoning 🛜 General Broadcast 🔀 Selective Mediation 🤼 Versus Logit-Lens ✏️ Free Chat Blog Code Weights Contact

related reading

• Neuronpedianeuronpedia.org
• LLM Visualizationbbycroft.net
• GPT2-SMALL · 7-RES-JB · 10199 ｜ Neuronpedianeuronpedia.org
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4. · GitHubgithub.com
• GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible. · GitHubgithub.com
• AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
• GitHub - x1xhlol/system-prompts-and-models-of-ai-tools: FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Tragithub.com
• Parsed | Custom, interpretable AI systems that continuously learnparsed.com
• GitHub - jacobhilton/deep_learning_curriculum: Language model alignment-focused deep learning curriculum · GitHubgithub.com
• Branches · HazyResearch/intelligence-per-watt · GitHubgithub.com
• GitHub - affaan-m/ECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. · GitHubgithub.com
• Denis Shiryaev | AI & ML Projectsshir-man.com