© 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. 44413
    Prev
    Next
    INDEX
    Explanations

    Sieve Of Erastothenes

    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
    æĬ½åĩº
    -0.08
    /cms
    -0.07
    ä¼´
    -0.07
    Ł
    -0.07
    adius
    -0.07
     consolidated
    -0.07
     averaged
    -0.06
    .defer
    -0.06
    æĮ«
    -0.06
    ç¿ģ
    -0.06
    POSITIVE LOGITS
    ếp
    0.08
     наÑĩин
    0.08
    ynes
    0.07
    大åѦåĩºçīĪ社
    0.07
    insel
    0.07
    eyond
    0.07
    ulangan
    0.07
    obo
    0.07
     formed
    0.07
     Beyond
    0.07
    Activations Density 0.002%

    No Known Activations