© 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. 9797
    Prev
    Next
    INDEX
    Explanations

    experts and educators

    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
    两èĢħ
    -0.11
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.09
    åħ©èĢħ
    -0.09
    äºĮèĢħ
    -0.09
    两èĢħçļĦ
    -0.08
     kedua
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    两éĥ¨åĪĨ
    -0.08
    urre
    -0.08
    ä¸īéĥ¨æĽ²
    -0.07
    POSITIVE LOGITS
     altrett
    0.17
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.15
    ãģĿãĤĮãģŀãĤĮ
    0.13
    åĪĨåĪ«æĺ¯
    0.13
    ä¹ĭå¤ļ
    0.13
     подÑĢÑıд
    0.12
    ä¸įåIJĮç¨ĭ度
    0.12
     ê°ģê°ģ
    0.11
    ãģĨãģ¡
    0.11
    缺ä¸Ģä¸įåı¯
    0.11
    Activations Density 0.622%

    No Known Activations