© 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. 7001
    Prev
    Next
    INDEX
    Explanations

    ticks below 0 or 1

    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
    ongyang
    -0.07
    opedia
    -0.07
     Ilmais
    -0.07
    бал
    -0.07
    ä¹Łæĺ¯å¦ĤæѤ
    -0.07
    oes
    -0.07
    ukul
    -0.07
    eh
    -0.07
    以ä¸ĬåĨħ容
    -0.07
    æıIJä¾Ľä¸Ģç§į
    -0.07
    POSITIVE LOGITS
    isson
    0.08
    ëŀĢ
    0.07
    ä»Ģä¹Īåij¢
    0.07
    .just
    0.07
    ìĿ´ëŀĢ
    0.06
    åij¢
    0.06
    æĮĩ
    0.06
     sendiri
    0.06
     Levy
    0.06
    ugia
    0.06
    Activations Density 0.012%

    No Known Activations