© 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. 37524
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

    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
    é¢Ĭ
    -0.07
    Õ¹
    -0.07
    /lg
    -0.07
    aub
    -0.07
    inator
    -0.07
    åѦæ³ķ
    -0.07
    ype
    -0.07
    å¼ĢåѦ第ä¸Ģ课
    -0.07
    羣çļĦ太
    -0.07
    ;n
    -0.07
    POSITIVE LOGITS
    éĽħ
    0.07
    éĢĨ
    0.07
     **.**
    0.07
    usser
    0.07
    æ¨
    0.07
     since
    0.07
    éļ»
    0.06
    ç¿ĺ
    0.06
    欧
    0.06
    æµģéĢļ
    0.06
    Activations Density 0.001%

    No Known Activations