© 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. 44017
    Prev
    Next
    INDEX
    Explanations

    equations, variables, and derivatives

    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
    æĢ»ç½²
    -0.08
     sourceMappingURL
    -0.07
    kker
    -0.07
    åĿļå®ļçļĦ
    -0.07
    ruz
    -0.07
    ãģ£ãģįãĤĬ
    -0.07
    ajari
    -0.07
     Litt
    -0.07
    æĹłæīĢ
    -0.07
    rier
    -0.07
    POSITIVE LOGITS
     Netto
    0.07
     powers
    0.07
    è¿Ļ两ç§į
    0.06
     favoritos
    0.06
     favorita
    0.06
     gross
    0.06
    åĴĮé£İ
    0.06
    é£İåIJ¹
    0.06
    å¨ľå¨ľ
    0.06
    æĭīèIJ¨
    0.06
    Activations Density 0.010%

    No Known Activations