© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61908
    Prev
    Next
    INDEX
    Explanations

    See http

    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
    æĺ¯æĹł
    -0.07
    bert
    -0.07
    czyk
    -0.07
    oni
    -0.06
     dessen
    -0.06
    lena
    -0.06
     fragile
    -0.06
    loo
    -0.06
    è¿ĩéĶĻ
    -0.06
    ä¸įèĢIJ
    -0.06
    POSITIVE LOGITS
    ëŀij
    0.08
    abant
    0.07
    niÄį
    0.07
    ä¸ĢæĿ¡é¾Ļ
    0.07
     Rú
    0.07
    æĢ»èĢĮè¨Ģä¹ĭ
    0.07
     trasc
    0.07
    é»ĺé»ĺåľ°
    0.07
    wig
    0.07
    ำà¸Ļ
    0.06
    Activations Density 0.226%

    No Known Activations