© 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. 44543
    Prev
    Next
    INDEX
    Explanations

    surface analysis

    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
    eration
    -0.10
    gers
    -0.08
    eries
    -0.08
    erator
    -0.08
    umente
    -0.08
     thầm
    -0.08
    ä¸įåĨ³
    -0.08
     ÑģÑĢока
    -0.07
    -disable
    -0.07
    anium
    -0.07
    POSITIVE LOGITS
    less
    0.10
    hood
    0.10
    ugin
    0.09
    ciano
    0.08
    éĿ¢çļĦ
    0.08
    Ùĭ
    0.08
    stech
    0.08
    ä¸ĬçļĦ
    0.08
     ÑĢаздела
    0.08
    tte
    0.08
    Activations Density 0.057%

    No Known Activations