© 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. 44632
    Prev
    Next
    INDEX
    Explanations

    abdominal obesity

    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
    ä¸İç»´æĬ¤
    -0.09
    edia
    -0.08
    stown
    -0.08
    schap
    -0.08
    ¦
    -0.08
    é¬ĵ
    -0.07
    /error
    -0.07
    żd
    -0.07
    头ä¸ĬçļĦ
    -0.07
    lew
    -0.07
    POSITIVE LOGITS
    /body
    0.09
    crawl
    0.09
    èħ¹
    0.08
    -mounted
    0.08
    èĤļ
    0.08
    éĥ¨çļĦ
    0.08
    alais
    0.08
     живоÑĤа
    0.08
    -wide
    0.08
     area
    0.07
    Activations Density 0.085%

    No Known Activations