© 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. 56491
    Prev
    Next
    INDEX
    Explanations

    points in time or stages

    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
    æѤæĸĩ
    -0.07
    æĺĮåİ¿
    -0.06
    enko
    -0.06
     Gì
    -0.06
    _MISC
    -0.06
    ück
    -0.06
     dĩ
    -0.06
    <|box_end|>
    -0.06
    /media
    -0.06
    è¿ĻåĦ¿
    -0.06
    POSITIVE LOGITS
    ../
    0.07
    à¸Ĺาà¸ĩà¸ģาร
    0.06
    å·¥ä½ľå²Ĺä½į
    0.06
    áng
    0.06
    æī«ä¸Ģæī«
    0.06
    arpa
    0.06
    araf
    0.06
    cul
    0.06
     sorry
    0.06
    æ¯ıéĢ¢
    0.06
    Activations Density 0.567%

    No Known Activations