© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    date or title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     -
    -0.06
     above
    -0.06
     жел
    -0.06
    usters
    -0.06
    +xml
    -0.06
     Javas
    -0.06
    åģĩ
    -0.06
    Ø·
    -0.06
    åIJĮä¸Ĭ
    -0.06
    æīĩ
    -0.06
    POSITIVE LOGITS
    _BEGIN
    0.09
    ãģ¯ãģĺãĤģ
    0.09
    æĪijåħĪ
    0.09
    é¦ĸåħĪéľĢè¦ģ
    0.08
    伦
    0.08
    ÐłÐ¾
    0.08
    第ä¸Ģ课
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    å¼ķè¨Ģ
    0.08
    åīįè¨Ģ
    0.08
    Activations Density 3.037%

    No Known Activations