© 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. 9748
    Prev
    Next
    INDEX
    Explanations

    coding, distributed, TokenType

    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
    该éĻ¢
    -0.07
    å¾Ĺ天
    -0.06
    æ±Ĥå®ŀ
    -0.06
     bona
    -0.06
    çİ°åľ¨å°±
    -0.06
    OUN
    -0.06
    .sym
    -0.06
    vlc
    -0.06
     perl
    -0.06
    éļ¾çľĭ
    -0.05
    POSITIVE LOGITS
    watan
    0.08
    bat
    0.08
    æ³½æ°ij
    0.07
    ruta
    0.07
    obile
    0.07
    ¿
    0.07
    æĪij们ç»ı常
    0.07
    ãģĵãĤĮãĤĤ
    0.07
    alaman
    0.07
    tü
    0.07
    Activations Density 0.050%

    No Known Activations