© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42581
    Prev
    Next
    INDEX
    Explanations

    refers to

    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
    èĢĮ代ä¹ĭ
    -0.08
    olum
    -0.08
    ucht
    -0.08
    说ä¸Ģåı¥
    -0.07
    Åľ
    -0.07
    ä¹ĭåIJį
    -0.07
    eis
    -0.07
    AccessException
    -0.07
    ensibly
    -0.07
    æĸ°çIJĨ念
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.12
    ä½Ĩä¸įéĻIJäºİ
    0.10
    éĤ£ç§į
    0.10
    çļĦå°±æĺ¯
    0.09
    è¿Ļæł·ä¸Ģç§į
    0.08
    ä¸įè¿ĩåľ¨
    0.08
     viá»ĩc
    0.08
    åľ¨åĨħçļĦ
    0.07
    éĤ£ç¨®
    0.07
    çļĦå°±
    0.07
    Activations Density 0.162%

    No Known Activations