© 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. 25060
    Prev
    Next
    INDEX
    Explanations

    defining python functions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    _nullable
    -0.08
     {}.
    -0.08
    icur
    -0.08
    ÅĤuga
    -0.07
    èĢģå¸Īåľ¨
    -0.07
    estra
    -0.07
    .vendor
    -0.07
    TokenType
    -0.07
    æĥħ趣
    -0.07
    åĮ»ç§ij大åѦéĻĦå±ŀ
    -0.06
    POSITIVE LOGITS
    âĪ½
    0.06
    ugal
    0.06
    å¤ļ大
    0.06
    ä¹ĭåħī
    0.06
    รม
    0.06
    æľīå¤ļå°ij
    0.06
    lub
    0.06
     puss
    0.06
    ÙĨÙĪ
    0.06
    ร
    0.05
    Activations Density 0.020%

    No Known Activations