© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51959
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

    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
    ba
    -0.07
    std
    -0.07
    soon
    -0.07
    lic
    -0.07
    /std
    -0.07
    oub
    -0.07
    efs
    -0.06
    syscall
    -0.06
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.06
    è¯ģæį®
    -0.06
    POSITIVE LOGITS
    æª
    0.09
    ç¬ĥ
    0.07
    dos
    0.07
    ä¸įçł´
    0.07
    åłĤ
    0.07
     hall
    0.07
    æ¿Ģ
    0.07
     messe
    0.07
    atik
    0.07
    inz
    0.07
    Activations Density 0.003%

    No Known Activations