© 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. 59887
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    ç³ľ
    -0.08
    éģįå¸ĥ
    -0.07
     ãħ£
    -0.07
     insulated
    -0.07
    éĺħåħµ
    -0.07
    peria
    -0.07
    /posts
    -0.07
    годи
    -0.07
     maneuver
    -0.06
     manoe
    -0.06
    POSITIVE LOGITS
     Polynomial
    0.08
     polynomial
    0.08
    åģľå·¥
    0.08
    ifact
    0.08
     Blow
    0.07
    çŁ¿ä¸ļ
    0.07
    Chip
    0.07
    åķĥ
    0.07
    azzi
    0.07
    åĽ¢åľĨ
    0.07
    Activations Density 0.017%

    No Known Activations