© 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. 16487
    Prev
    Next
    INDEX
    Explanations

    induced by

    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
    _pack
    -0.08
    ypad
    -0.08
    positor
    -0.07
    缮çļĦå°±æĺ¯
    -0.07
    odar
    -0.07
    åĩ
    -0.07
    목ìłģ
    -0.07
     Dadurch
    -0.06
    riminator
    -0.06
    idth
    -0.06
    POSITIVE LOGITS
     underlying
    0.07
    ä¾Ŀæīĺ
    0.07
    åİŁæĸĻ
    0.07
    éĢīæĿIJ
    0.07
    åİŁæĿIJæĸĻ
    0.06
    产ä¸ļç»ĵæŀĦè°ĥæķ´
    0.06
    åıªåĽł
    0.06
    edBy
    0.06
    åıĸæĿIJ
    0.06
    strncmp
    0.06
    Activations Density 0.386%

    No Known Activations