AnalysisAI ModelsJuly 6, 2026
Anthropic discovers Claude's emergent 'J-space' for silent reasoning

Anthropic's research reveals Claude spontaneously developed a set of internal neural patterns called J-space, allowing it to think about concepts like "spider" without outputting them. These patterns emerged naturally during training and enable Claude to both use them for reasoning and report on them when asked.
7 sources
A global workspace in language modelsanthropic.com
The J-space (named after the Jacobian, the mathematical technique we used) is different from...x.com
Anthropic's new "J-lens" reveals a silent workspace inside Claude that mirrors a leading theory of consciousnessventurebeat.com
Anthropic found a hidden space where Claude puzzles over conceptstechnologyreview.com
What’s at the center of Claude’s mind?youtube.com