© 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. 40949
    Prev
    Next
    INDEX
    Explanations

    homework, results, reason

    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
    ç¨į
    -0.07
    ...).
    -0.07
    +,
    -0.07
    +)
    -0.07
    Stuff
    -0.06
    çѱ
    -0.06
    ?):
    -0.06
    :")
    -0.06
    åľ¨æīĢ
    -0.06
    idia
    -0.06
    POSITIVE LOGITS
    ebas
    0.08
    秫
    0.07
    بس
    0.07
     ãģªãģ©
    0.06
    εί
    0.06
    æĸ°åĬłåĿ¡
    0.06
    ç»Ļ客æĪ·
    0.06
    à¸Īริà¸ĩ
    0.06
    æģŃåĸľ
    0.06
    è¿ĺæľīäºĽ
    0.06
    Activations Density 0.014%

    No Known Activations