© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44098
    Prev
    Next
    INDEX
    Explanations

    consisting of, born in, total of, occur every

    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
    æĮ¯
    -0.07
    éĺ³æĺ¥
    -0.07
    pcf
    -0.07
    riding
    -0.07
    rzy
    -0.06
    uff
    -0.06
    çĸı导
    -0.06
    .Listener
    -0.06
    .iOS
    -0.06
    å·¥ä½ľçļĦåIJĮæŶ
    -0.06
    POSITIVE LOGITS
     Hardcover
    0.07
    andom
    0.07
    hoff
    0.07
    Dependencies
    0.07
    eref
    0.07
    enner
    0.06
    å°ijæľī
    0.06
     scop
    0.06
    _minor
    0.06
    Å«d
    0.06
    Activations Density 0.001%

    No Known Activations