© 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. 40231
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    ervo
    -0.09
    abia
    -0.08
    nard
    -0.07
    èĿī
    -0.07
    é£İåIJ¹
    -0.07
    æĢ
    -0.07
    eworthy
    -0.07
    stoff
    -0.07
     Vernon
    -0.07
    æĿ¥æºIJç½ij绾
    -0.07
    POSITIVE LOGITS
    ä¼°è¨Ī
    0.07
    估计
    0.07
    ehren
    0.07
    oa
    0.07
    åĢ¾åŁİ
    0.06
    :)
    0.06
    ÙĬØ´
    0.06
    acco
    0.06
    _fetch
    0.06
    _estimate
    0.06
    Activations Density 0.002%

    No Known Activations