© 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. 44723
    Prev
    Next
    INDEX
    Explanations

    specialized or dedicated

    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
    ÙĦع
    -0.11
    اء
    -0.09
    ابÛĮ
    -0.08
    Ñģпол
    -0.08
    .githubusercontent
    -0.08
    åĬ¨çļĦ
    -0.08
    zicht
    -0.08
    egend
    -0.08
    اث
    -0.07
    agli
    -0.07
    POSITIVE LOGITS
    ively
    0.08
    ivity
    0.08
    zed
    0.08
    ر
    0.08
    aghetti
    0.08
    itized
    0.08
    人士
    0.07
    à¹Ģà¸Īาะ
    0.07
    -purpose
    0.07
    fabs
    0.07
    Activations Density 0.050%

    No Known Activations