© 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. 56346
    Prev
    Next
    INDEX
    Explanations

    thesis statement

    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
    obre
    -0.08
    秸
    -0.07
    -turned
    -0.07
    ceg
    -0.07
    acken
    -0.07
    exas
    -0.07
    orsi
    -0.07
    æ³ķå¾ĭä¿ĿæĬ¤
    -0.07
    çļĦèĥĮæĻ¯
    -0.07
    bery
    -0.06
    POSITIVE LOGITS
     determined
    0.09
     determination
    0.09
    ç¡®å®ļ
    0.08
     based
    0.08
     ditentukan
    0.08
    ä¾Ŀæį®
    0.07
    æĺ¯æł¹æį®
    0.07
     Determin
    0.07
    ç¡®å®ļçļĦ
    0.07
     dá»±a
    0.07
    Activations Density 0.037%

    No Known Activations