© 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. 60616
    Prev
    Next
    INDEX
    Explanations

    body building, body of, bodyworks

    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
    ï¸İ
    -0.11
    人æ°ijåĮ»éĻ¢
    -0.10
    ceptar
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    Allem
    -0.09
    erst
    -0.09
    ensburg
    -0.09
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    ighted
    -0.08
    möglichkeit
    -0.08
    POSITIVE LOGITS
    hood
    0.13
    åĬĽè¡Į
    0.09
    guards
    0.09
    ики
    0.09
    اء
    0.08
    cules
    0.08
    /body
    0.07
    wide
    0.07
    -wide
    0.07
     ÑĤела
    0.07
    Activations Density 0.061%

    No Known Activations