© 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. 56219
    Prev
    Next
    INDEX
    Explanations

    contributions

    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
    estre
    -0.08
    urgia
    -0.08
    æݥ轨
    -0.08
    æĿ¡ä»¶ä¸ĭ
    -0.07
    estr
    -0.07
    ÃŃce
    -0.07
    ãģĹãģıãģ¯
    -0.07
    .appspot
    -0.07
    formance
    -0.07
    datatable
    -0.07
    POSITIVE LOGITS
    æĿ¥èĩª
    0.12
    æĿ¥èĩªäºİ
    0.11
    ä¾Ĩèĩª
    0.10
     from
    0.10
    主è¦ģæĿ¥èĩª
    0.09
    /value
    0.08
    à¸Īาà¸ģ
    0.08
    æĿ¥èĩªç½ij绾
    0.08
     дÑı
    0.08
    from
    0.08
    Activations Density 0.007%

    No Known Activations