© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27079
    Prev
    Next
    INDEX
    Explanations

    countries and technical terms

    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
    izzi
    -0.07
    ä¸İçİ°å®ŀ
    -0.06
    ä»Ĺ
    -0.06
    人æ°ijæ³ķéĻ¢
    -0.06
    icona
    -0.06
    druk
    -0.06
    æĿī
    -0.06
    mana
    -0.06
    -
    -0.06
    .pag
    -0.06
    POSITIVE LOGITS
    ê²IJ
    0.08
    _ctxt
    0.07
    ä»ĬæĹ¥å¤´æĿ¡
    0.07
    uluh
    0.07
    вÑĢ
    0.07
    ipur
    0.07
    ueb
    0.07
    vét
    0.07
    çľĭä½ł
    0.07
     Städ
    0.07
    Activations Density 0.068%

    No Known Activations