© 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. 47142
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    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
    æ¥ļæ¥ļ
    -0.08
    æĸľåĿ¡
    -0.07
     Toto
    -0.07
     Nairobi
    -0.07
    æ·ĭ
    -0.07
    ä¸įéķ¿
    -0.07
    çĮ®èº«
    -0.07
    andon
    -0.06
    rzy
    -0.06
     Saigon
    -0.06
    POSITIVE LOGITS
    æ°´ä»Ļ
    0.08
    èĭ¦å¿ĥ
    0.07
    amework
    0.07
    vaard
    0.07
     Pear
    0.07
    家é£İ
    0.07
    éķĤ
    0.07
    itaine
    0.07
    urrenc
    0.07
    recur
    0.06
    Activations Density 0.003%

    No Known Activations