© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    technical terms or nodes

    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
    对åħ¬åı¸çļĦ
    -0.08
    æĭ¥
    -0.07
    åĭ¿æī°
    -0.07
    æĮĤæľº
    -0.07
    æ´ĭ
    -0.07
    ä¹Łå¸ĮæľĽ
    -0.07
    æīĭæı¡
    -0.07
    ruhe
    -0.07
    第ä¸īç§į
    -0.07
    hower
    -0.07
    POSITIVE LOGITS
    ä¸Ģä¸Ģ
    0.07
    ä¸İåIJĦ
    0.07
    éĢIJä¸Ģ
    0.07
    åľ¨åIJĦ
    0.07
    "They
    0.07
    clus
    0.07
    oyo
    0.06
    é¢IJ
    0.06
    è·Łä»ĸ们
    0.06
    对åIJĦ
    0.06
    Activations Density 0.138%

    No Known Activations