© 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. 27998
    Prev
    Next
    INDEX
    Explanations

    last checked

    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
    ä½ķæĸ¹
    -0.08
    regen
    -0.07
    积
    -0.07
    æ¬ł
    -0.07
    expect
    -0.07
     expect
    -0.06
     almost
    -0.06
    inson
    -0.06
    ç»Ĭ
    -0.06
    ISTR
    -0.06
    POSITIVE LOGITS
    ืà¸Ńà¸ĩ
    0.09
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    licos
    0.08
    aldo
    0.08
    awat
    0.07
    almente
    0.07
    ÑĪÑĤо
    0.07
    åħ³éĹŃçªĹåı£
    0.07
    irken
    0.07
    è¿ĩç¥ŀ
    0.07
    Activations Density 0.001%

    No Known Activations