© 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. 25097
    Prev
    Next
    INDEX
    Explanations

    wanting something

    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
    è°
    -0.07
    æľ
    -0.06
    al
    -0.06
    .ent
    -0.06
     indef
    -0.06
    èĭ¥æľīæīĢæĢĿ
    -0.06
    ç¼¥
    -0.06
    zec
    -0.06
     Ker
    -0.06
    /d
    -0.06
    POSITIVE LOGITS
    rato
    0.08
    imy
    0.08
    CurrentValue
    0.08
    othe
    0.07
    对åįİ
    0.07
    ÑĢаÑĤоÑĢ
    0.07
    ÙĪدÛĮ
    0.07
    jør
    0.07
    imax
    0.07
    WithType
    0.07
    Activations Density 0.002%

    No Known Activations