© 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. 55165
    Prev
    Next
    INDEX
    Explanations

    case identifier CV

    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
    <<<<<<<
    -0.07
    kert
    -0.07
    éĻĪå¿Ĺ
    -0.06
    acock
    -0.06
     tslint
    -0.06
    ê³
    -0.06
    åľ¨åĨĮ
    -0.06
    ftware
    -0.06
    istant
    -0.06
    obi
    -0.06
    POSITIVE LOGITS
    åIJĦç§įåIJĦæł·
    0.10
    éĺ¿æĭī伯
    0.09
    ä¸įåı¯æĢĿè®®
    0.09
    åIJĮä¸Ĭ
    0.09
    åĬłæĭ¿å¤§
    0.09
    åĭĩå¾Ģ缴åīį
    0.08
    äºĶé¢ľåħŃèī²çļĦ
    0.08
    两åѦä¸Ģåģļ
    0.08
    æĸ°åĬłåĿ¡
    0.08
    dddd
    0.08
    Activations Density 0.037%

    No Known Activations