© 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. 31761
    Prev
    Next
    INDEX
    Explanations

    .Complete

    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
    le
    -0.07
    æn
    -0.07
    ingle
    -0.07
    entie
    -0.07
    è¡¥
    -0.07
    æ²ĥæĸ¯
    -0.07
    adu
    -0.07
     licensors
    -0.07
    anic
    -0.07
    hic
    -0.07
    POSITIVE LOGITS
    ä½łæķ¢
    0.07
    .Complete
    0.07
    UNK
    0.06
    trate
    0.06
    essler
    0.06
    大河
    0.06
     Polic
    0.06
    ciano
    0.06
    ause
    0.06
    åľ¨è§Ħå®ļ
    0.06
    Activations Density 0.001%

    No Known Activations