© 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. 43283
    Prev
    Next
    INDEX
    Explanations

    android bundle

    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
    urin
    -0.07
    arine
    -0.07
     заÑĤÑı
    -0.07
    ibaldi
    -0.06
    ãģįãģª
    -0.06
    æİĸ
    -0.06
     inc
    -0.06
    hur
    -0.06
    åľ¨è¯»
    -0.06
    INGTON
    -0.06
    POSITIVE LOGITS
    åĿij
    0.08
    à¹Ģà¸Ľà¸£à¸µà¸¢à¸ļ
    0.08
    elig
    0.08
     tại
    0.07
    å·´åħĭ
    0.07
    lıklı
    0.07
    å£
    0.07
    MOVED
    0.07
    aty
    0.07
    æĦŁäºº
    0.06
    Activations Density 0.001%

    No Known Activations