© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    fire brigade, ListView, Activity

    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
    çĽĪçĽĪ
    -0.08
    á»Ļn
    -0.07
    alp
    -0.07
    æĸĩåĮĸä¼łåªĴæľīéĻIJåħ¬åı¸
    -0.07
    zs
    -0.07
    åľ¨åľº
    -0.07
    плика
    -0.07
    延
    -0.07
    åı°ä¸ĭ
    -0.07
    ÙħÙĪÙĦ
    -0.07
    POSITIVE LOGITS
     probably
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    大æ¦Ĥæĺ¯
    0.08
     presumably
    0.08
    åı¯èĥ½åľ¨
    0.07
    好åĥıæĺ¯
    0.07
    åı¯èĥ½å¯¹
    0.07
     probabilmente
    0.07
     maybe
    0.07
    æĪĸåħ¶ä»ĸ
    0.07
    Activations Density 0.069%

    No Known Activations