© 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. 8561
    Prev
    Next
    INDEX
    Explanations

    physics and math notation

    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
    ä¸ĭå±Ĥ
    -0.07
    auer
    -0.07
    å¤įä¹łèµĦæĸĻ
    -0.06
    çļĦéĹ®é¢ĺæĺ¯
    -0.06
    缺çĤ¹æĺ¯
    -0.06
    áp
    -0.06
    üy
    -0.06
    _INFORMATION
    -0.06
    尽管
    -0.06
    大米
    -0.06
    POSITIVE LOGITS
    æ¨
    0.08
    ä¸įæĢĿ
    0.08
    egral
    0.07
     Hug
    0.07
     warranted
    0.07
    omatic
    0.07
    [ix
    0.07
    помним
    0.07
    gs
    0.07
    loomberg
    0.07
    Activations Density 0.003%

    No Known Activations