© 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. 43344
    Prev
    Next
    INDEX
    Explanations

    programming types and locations

    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
    çİ
    -0.07
    ç¬ijèµ·æĿ¥
    -0.07
    è¯ĿæĿ¥
    -0.07
    uduk
    -0.06
    èĢĮ使
    -0.06
    iz
    -0.06
    æĥħåĨµåĪĨæŀIJ
    -0.06
    esses
    -0.06
     Tutt
    -0.06
    gl
    -0.06
    POSITIVE LOGITS
    edic
    0.08
    æĿĤè´§
    0.08
    æ²ģ
    0.08
    หà¸Ļ
    0.08
    ,void
    0.08
    reator
    0.08
     Juta
    0.08
    bservice
    0.08
    pard
    0.07
    _dependency
    0.07
    Activations Density 0.523%

    No Known Activations