© 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. 34823
    Prev
    Next
    INDEX
    Explanations

    CH followed by .sub

    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
    adelphia
    -0.09
    zilla
    -0.08
    enza
    -0.08
    éĺ¿æĭī伯
    -0.08
    æ¡¥åĮº
    -0.08
    онеÑĢ
    -0.08
    ToBounds
    -0.07
    ç»ıæµİåѦéĻ¢
    -0.07
    á»ģn
    -0.07
    íĮħ
    -0.07
    POSITIVE LOGITS
    panse
    0.07
    èµ·çļĦ
    0.07
    olds
    0.07
     vez
    0.07
    åĿĤ
    0.06
    ovich
    0.06
    год
    0.06
    æĹıèĩªæ²»
    0.06
     (
    0.06
    èĨĬ
    0.06
    Activations Density 0.002%

    No Known Activations