© 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. 22077
    Prev
    Next
    INDEX
    Explanations

    parameter documentation

    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
    âĢ¦âĢ¦ãĢĤ
    -0.10
    ;/*
    -0.09
    âĢ¦),
    -0.08
    :],
    -0.07
     Amaz
    -0.07
     mach
    -0.07
    âĢ¦).
    -0.07
    ordinate
    -0.07
    çļĦäºĭå®ŀ
    -0.07
    abe
    -0.07
    POSITIVE LOGITS
    ศ
    0.08
    ä¸ĭåIJĮ
    0.07
    %s
    0.06
    ä¼¼
    0.06
    ãģ¨ãģĵãĤįãģ¯
    0.06
     */
    0.06
    wirkung
    0.06
    èıģ
    0.06
    MethodName
    0.06
    hs
    0.06
    Activations Density 0.039%

    No Known Activations