© 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. 64767
    Prev
    Next
    INDEX
    Explanations

    each of

    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
    纲
    -0.08
    人åķĬ
    -0.08
    ико
    -0.08
    )|(
    -0.08
    èĬ±èįī
    -0.08
    [++
    -0.07
    ä¸Ģ个åı«
    -0.07
    ä¸Ńæݧ
    -0.07
    人èĥ½
    -0.07
    浦路
    -0.07
    POSITIVE LOGITS
    urez
    0.07
    æ¯ıä¸ĢåIJį
    0.06
    絡
    0.06
     entirety
    0.06
    æīĢæľīçļĦ
    0.06
    æ¯ıä¸Ģ
    0.06
     everybody
    0.06
    çļĦæ¯ıä¸Ģ
    0.06
    èĭ¥æĺ¯
    0.06
    arg
    0.06
    Activations Density 0.283%

    No Known Activations