© 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. 25608
    Prev
    Next
    INDEX
    Explanations

    Chinese person, hair, or play

    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
    agni
    -0.07
    åİĨ
    -0.07
    Least
    -0.07
    миÑĢ
    -0.07
    asures
    -0.07
    _least
    -0.06
    lest
    -0.06
     Flick
    -0.06
    æĭħå¿ĥ
    -0.06
     |_|
    -0.06
    POSITIVE LOGITS
    æ¯Ķä»ĸ
    0.13
    æĽ´é«ĺçļĦ
    0.13
    æ¯Ķä½ł
    0.13
    æĽ´å°ı
    0.12
    æľīæĽ´
    0.12
    æĽ´é«ĺ
    0.12
    æ¯ĶæĪij
    0.11
    éĥ½æ¯Ķ
    0.11
    ä¼ĺäºİ
    0.11
    æľīæĽ´å¥½çļĦ
    0.11
    Activations Density 0.083%

    No Known Activations