© 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. 19549
    Prev
    Next
    INDEX
    Explanations

    nationalities and place names

    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
    toInt
    -0.07
    ÑģлÑĥжи
    -0.07
    igt
    -0.07
     Crescent
    -0.07
    ừa
    -0.07
    è¿Ļæł·çļĦäºĭæĥħ
    -0.07
    ادر
    -0.07
    luv
    -0.07
    人æ°ijåĮ»éĻ¢
    -0.07
    çµ±ä¸Ģ
    -0.07
    POSITIVE LOGITS
    weiler
    0.07
    isson
    0.07
    æĻ®éĢļ
    0.06
    eping
    0.06
    ormal
    0.06
    çļĦæķĪçİĩ
    0.06
    zez
    0.06
    oÅĽci
    0.06
    comb
    0.06
    gmail
    0.06
    Activations Density 0.038%

    No Known Activations