© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    list tail or .rest

    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
    pha
    -0.08
    phe
    -0.07
    zgl
    -0.07
    fers
    -0.07
    ãģ¾ãģ¾
    -0.07
    ç»ĻæĪij们带æĿ¥
    -0.07
    åıĮæĸ¹
    -0.07
     interle
    -0.07
    æĻĵ举
    -0.07
    lene
    -0.07
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.09
     ëĤĺ머ì§Ģ
    0.08
    æ¶ķ
    0.07
    éĻ¤äºĨ
    0.07
    汪æ´ĭ
    0.07
     кÑĢоме
    0.07
    éĻ¤
    0.07
     Aside
    0.07
    à¹Ģหลืà¸Ń
    0.07
    .gca
    0.06
    Activations Density 0.030%

    No Known Activations