© 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. 51377
    Prev
    Next
    INDEX
    Explanations

    comparisons using 'same' or 'similar'

    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
    lÃł
    -0.08
    ä¹Łåı¯èĥ½æĺ¯
    -0.07
    ίδα
    -0.07
    å°ļ
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    èĩªè¡Į
    -0.07
    æ°´åľŁ
    -0.07
    elman
    -0.07
    obo
    -0.07
    lah
    -0.07
    POSITIVE LOGITS
    缸åIJĮçļĦ
    0.09
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    åIJĮä¸Ģ个
    0.08
    约èĢĮåIJĮ
    0.08
    åIJĦèĩªçļĦ
    0.08
    éĥ½è®¤ä¸º
    0.08
    åIJĮæł·çļĦ
    0.07
    åIJĦèĩª
    0.07
     identical
    0.07
    ä¸įåIJĮçļĦæĺ¯
    0.07
    Activations Density 0.007%

    No Known Activations