© 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. 64260
    Prev
    Next
    INDEX
    Explanations

    // comments and code headers

    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
    LER
    -0.08
    代表
    -0.07
     Lew
    -0.07
    çī¹åĪ«å£°æĺİ
    -0.07
    .rar
    -0.07
    orex
    -0.07
    ´t
    -0.07
     Ler
    -0.07
    cze
    -0.07
    ihan
    -0.07
    POSITIVE LOGITS
    éģŃ
    0.08
    gl
    0.07
    欢åĸľ
    0.07
    é¡ĺ
    0.07
    unis
    0.06
     ----------------------------------------------------------------
    0.06
    //=
    0.06
    ιÏĥη
    0.06
    æ·ĭæ¼ĵ
    0.06
    /gl
    0.06
    Activations Density 1.092%

    No Known Activations