© 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. 8161
    Prev
    Next
    INDEX
    Explanations

    comment markers // and #

    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
    eltas
    -0.07
    åijĹ
    -0.07
    èĪį
    -0.06
    adena
    -0.06
    rossover
    -0.06
    çļĦåķĬ
    -0.06
    ä¸¤åľº
    -0.06
     pese
    -0.06
    IEWS
    -0.06
    adors
    -0.06
    POSITIVE LOGITS
    ulat
    0.08
    ulam
    0.08
    ç§ij大
    0.07
    缮çļĦæĺ¯
    0.07
    noinspection
    0.07
    ä¸įåıĬå¾ħ
    0.07
    æİĴè¡Įæ¦ľåįķ
    0.07
    ulitan
    0.07
    çļĦæīĢæľīä½ľåĵģ
    0.07
    mbH
    0.07
    Activations Density 0.171%

    No Known Activations