© 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. 49000
    Prev
    Next
    INDEX
    Explanations

    head coach

    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
    hung
    -0.07
    adop
    -0.07
     Raya
    -0.07
    åĴĮåĬªåĬĽ
    -0.07
    ìľ
    -0.07
    дÑĢо
    -0.06
    عÙĬد
    -0.06
    çĶ¨éĴ±
    -0.06
    æ¼ı
    -0.06
    ç§ijæĸ¯
    -0.06
    POSITIVE LOGITS
    arily
    0.08
    ãĥ¼ãĥĦ
    0.07
    ıcı
    0.07
    scr
    0.07
    /browse
    0.07
    Scroll
    0.07
    égor
    0.07
    æ··åIJĪåŀĭ
    0.07
    adge
    0.06
    aturally
    0.06
    Activations Density 0.015%

    No Known Activations