© 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. 64998
    Prev
    Next
    INDEX
    Explanations

    front end or programming contexts

    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
    ulte
    -0.07
    ng
    -0.07
    ä¹į
    -0.07
     deriv
    -0.07
    æľīä¸Ģå®ļçļĦ
    -0.07
    éĥİ
    -0.06
    sor
    -0.06
    oth
    -0.06
     natal
    -0.06
    {o
    -0.06
    POSITIVE LOGITS
    æĹ¢çĦ¶æĺ¯
    0.11
    èĻ½çĦ¶æĺ¯
    0.09
    符åIJĪæĿ¡ä»¶
    0.08
    æĹ¢çĦ¶å¦ĤæѤ
    0.07
    æѤ类
    0.07
    æĥŁä¸Ģ
    0.07
    åĽłä¸ºæĺ¯
    0.07
    ä¸įè¿Ľ
    0.07
    çļĦè¿Ļç§į
    0.07
     ãģĵãģ®ãĤĪãģĨãģª
    0.07
    Activations Density 0.263%

    No Known Activations