© 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. 9777
    Prev
    Next
    INDEX
    Explanations

    looks amazing

    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
    ostream
    -0.07
    icali
    -0.06
    ("{
    -0.06
    годи
    -0.06
     âĢ¦
    -0.06
     ..."
    -0.06
    çľģçļĦ
    -0.06
    âĢ¦
    -0.06
    <|fim_middle|>
    -0.06
    âĢ¦"
    -0.06
    POSITIVE LOGITS
    çļĦäºĭåĦ¿
    0.09
    versión
    0.08
    udir
    0.08
    ä¸ĢæľĿ
    0.08
    åķ¥
    0.08
    å¨ĥ
    0.07
    ä¸įå¤ļ说
    0.07
     Definitely
    0.07
    iraz
    0.07
    infos
    0.07
    Activations Density 0.467%

    No Known Activations