© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37563
    Prev
    Next
    INDEX
    Explanations

    U.S. or numbers

    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
    Negative Logits
    ures
    -0.07
    åł¡
    -0.07
    綾åIJĪ
    -0.07
    elh
    -0.07
    iefert
    -0.06
    综åIJĪ
    -0.06
    ()["
    -0.06
    itution
    -0.06
    otch
    -0.06
    æ³¥
    -0.06
    POSITIVE LOGITS
    åģļä¸ĢåIJį
    0.08
    маÑģ
    0.07
    ola
    0.07
    пÑĥ
    0.07
    ornado
    0.07
    arkin
    0.07
    escal
    0.06
    .CL
    0.06
    ibat
    0.06
    invert
    0.06
    Activations Density 0.070%

    No Known Activations