© 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. 24356
    Prev
    Next
    INDEX
    Explanations

    assigning parameter values

    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
    ;<
    -0.08
     ï¼Ī
    -0.07
     (#
    -0.06
     (<
    -0.06
    ;&
    -0.06
    tek
    -0.06
    etre
    -0.06
    ãģ¨ãģĦãģĨãģ®ãĤĤ
    -0.06
    dbe
    -0.06
    ,<
    -0.06
    POSITIVE LOGITS
    âĢ¦).
    0.09
    =
    0.09
    ׳×Ļת
    0.07
    ä¾ĽåĽ¾
    0.07
    æĺ¯åķĬ
    0.07
    ðŁĻĤ
    0.07
    âĢ¦),
    0.07
    vang
    0.07
    iette
    0.07
    âĢ¦,
    0.07
    Activations Density 0.227%

    No Known Activations