© 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. 37581
    Prev
    Next
    INDEX
    Explanations

    -based, -run, -ical, -type suffixes

    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
    occas
    -0.08
    audi
    -0.08
    aval
    -0.08
    essen
    -0.07
    ä¼łäºº
    -0.07
    ç§ijåѦåѦéĻ¢
    -0.07
    说好
    -0.07
    pje
    -0.07
    istine
    -0.07
    åŃ¦è¯´
    -0.07
    POSITIVE LOGITS
    åįģ足çļĦ
    0.07
    ãģĹãģĭ
    0.07
    ãģ°ãģĭãĤĬ
    0.07
    chy
    0.06
    æľ¬ç½ij
    0.06
    etak
    0.06
    tait
    0.06
    ignment
    0.06
    è´¯
    0.06
    ioned
    0.06
    Activations Density 0.237%

    No Known Activations