© 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. 45455
    Prev
    Next
    INDEX
    Explanations

    JOIN TABLE

    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
    ured
    -0.06
    ESH
    -0.06
    æģ¯
    -0.06
    å·¥
    -0.06
     median
    -0.05
    -0.05
    urkan
    -0.05
    缸ç»ĵåIJĪçļĦæĸ¹å¼ı
    -0.05
    æŦ
    -0.05
    毫åįĩ
    -0.05
    POSITIVE LOGITS
    è´¼
    0.08
    å®ĥä»¬åľ¨
    0.08
    è³Ĭ
    0.08
    .AutoComplete
    0.08
    ÄĻk
    0.08
    æĿĢçļĦ
    0.08
    ilha
    0.08
    Ùĩاب
    0.08
    øy
    0.08
    æĽ´å¤ļåĨħ容
    0.08
    Activations Density 0.001%

    No Known Activations