© 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. 40933
    Prev
    Next
    INDEX
    Explanations

    cannot prove that unless

    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
    æıIJæIJº
    -0.07
    usc
    -0.07
     CONC
    -0.07
    æ½Ł
    -0.07
     ÎŃγι
    -0.07
    oya
    -0.07
    è¿Ļåı¯æĺ¯
    -0.07
    çľĭçľĭåIJ§
    -0.06
    asih
    -0.06
    clone
    -0.06
    POSITIVE LOGITS
    ä¸įåŃĺåľ¨
    0.09
    羣å®ŀçļĦ
    0.08
    åıªèĥ½æĺ¯
    0.08
    è¯ģ
    0.08
    åıªèĥ½åľ¨
    0.08
    éĢ¼
    0.07
    èĢģèĢģå®ŀ
    0.07
    cene
    0.07
    ä¸įåħģ许
    0.07
    å®ŀéĻħæĥħåĨµ
    0.07
    Activations Density 0.004%

    No Known Activations