Anthropic Releases Global Workspace Interpretability Research

Anthropic released new interpretability research on July 6, 2026. The company announced that new interpretability research reveals an emergent mental workspace in Claude that holds internal thoughts that don't appear in the model's output. In a new paper we present evidence that a similar distinction has emerged in modern language models like Claude according to the Anthropic research page. Our experiments were inspired by a prominent theory in neuroscience that was developed to explain how conscious access works: the global workspace theory. This account pictures the brain as a collection of specialist systems that work in parallel unconsciously and largely in isolation from one another. A piece of information becomes consciously accessible when it gains entry to a small shared channel the workspace which is broadcast to other brain systems that can see it and make use of it. Based on our findings we think the J-space plays a similar workspace role in Claude the company said. This post is a short summary of a much more extensive research paper where you can find more detail on our experiments. We've also released a code repository with an open-source implementation of the core methods and have partnered with Neuronpedia to provide an interactive demo of our methods on open-weights models.