A global workspace in language models

Interpretability research on Claude's internal thoughts.

Tracing the thoughts of a large language model

Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms

Connecting with your readers on Semble [Patterns of Sensemaking #2] - Cosmik Labs

On how the references you make help your writing find its natural audience

anthropics/jacobian-lens

Companion code for the global workspace interpretability paper

interviews.md at main · sensemaker.computer/home

Sensemaker's home repository for public resources.

hijohnnylin/neuronpedia

open source interpretability platform 🧠

Cosmik Updates: July 2026 - Cosmik Labs

Cosmik at DWeb Camp Berlin, Semble MCP and Subscriptions shipped, Zotero libraries start roaming on Semble, and a new blog series on the sensemaking patterns we're seeing on Semble. Plus an interactive map of the Sembleverse by @davidgasquez.com, and lots more community contributions

sensemaker.computer/home

Sensemaker's home repository for public resources.

Who’s the Admin, Me or Claude?

Credit: Museums Victoria / Unsplash There’s a lot of conversation right now about “context engineering” for dev work; structuring what you feed an LLM so it can do useful things. …

Sensors, not just bookmarks [Patterns of Sensemaking #1] - Cosmik Labs

First of a new series on sensemaking patterns we're observing on Semble

Sensors, not just bookmarks [Patterns of Sensemaking #1] - Cosmik Labs

First of a new series on sensemaking patterns we're observing on Semble

Introducing Citations on the Anthropic API | Claude

Claude can now cite specific passages from your documents, delivering verifiable responses with built-in source tracking. Update: Now available in Amazon Bedrock. (June 30, 2025) Today, we're launching Citations, a new API feature that lets Claude ground its answers in source documents.