© 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. 45617
    Prev
    Next
    INDEX
    Explanations

    changes and code diffs

    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
    ãģĽ
    -0.07
    人æ°ijåħ±åĴĮåĽ½
    -0.07
    mess
    -0.06
    ale
    -0.06
    éĿŀåĨľ
    -0.06
    缴
    -0.06
    ENU
    -0.06
     Äijinh
    -0.06
     straight
    -0.06
    à°¿à°Ĥà°ļ
    -0.06
    POSITIVE LOGITS
    etus
    0.07
     oldValue
    0.07
    ylon
    0.07
     diffs
    0.07
    zuk
    0.07
    天çİĭ
    0.07
    urit
    0.07
    _CHANGED
    0.07
     Changed
    0.07
     оÑĤо
    0.07
    Activations Density 0.004%

    No Known Activations