© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55042
    Prev
    Next
    INDEX
    Explanations

    using something to do something

    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
    Negative Logits
    "';
    -0.10
    ä¸Ģç»ı
    -0.09
    为ä¹ĭ
    -0.09
    rolet
    -0.08
    :].
    -0.08
    andid
    -0.08
    epat
    -0.08
    转载请
    -0.07
    velle
    -0.07
    >;
    -0.07
    POSITIVE LOGITS
     inilah
    0.09
    便åı¯ä»¥
    0.08
    便åı¯
    0.08
    ä¸įéļ¾
    0.08
     _______,
    0.07
    orz
    0.07
    iola
    0.07
    ,is
    0.07
    æĪij们åı¯ä»¥
    0.07
     ÙģØ¥ÙĨÙĩ
    0.07
    Activations Density 0.254%

    No Known Activations