© 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. 47919
    Prev
    Next
    INDEX
    Explanations

    axis or average distance

    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
    rous
    -0.08
     Benson
    -0.08
    MU
    -0.08
    ieves
    -0.08
    á»ĵn
    -0.07
    prof
    -0.07
    gel
    -0.07
    gid
    -0.07
    -output
    -0.07
    æ²³å¸Ĥ
    -0.07
    POSITIVE LOGITS
    elum
    0.07
    /oauth
    0.07
    urt
    0.07
    å¹³åĿĩ
    0.07
    ä¿®
    0.06
     lenght
    0.06
    轴线
    0.06
    åĿı
    0.06
    ertz
    0.06
    ç¨
    0.06
    Activations Density 0.002%

    No Known Activations