© 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. 34763
    Prev
    Next
    INDEX
    Explanations

    function parameters or structure

    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
    zon
    -0.07
    гоÑĢа
    -0.07
    ulton
    -0.07
    кови
    -0.07
    ChangeListener
    -0.07
    онеÑĢ
    -0.07
    æĿ¾è½¯
    -0.06
     Garner
    -0.06
    odr
    -0.06
    æ¢Ŀ件
    -0.06
    POSITIVE LOGITS
    WithData
    0.09
    .getAction
    0.08
    name
    0.08
    AppName
    0.08
    æľīè¯Ŀ
    0.08
    мп
    0.07
    åIJį称
    0.07
    _exec
    0.07
    -name
    0.07
    åIJįçļĦ
    0.07
    Activations Density 0.268%

    No Known Activations