© 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. 4668
    Prev
    Next
    INDEX
    Explanations

    parts, pieces, components

    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
    ADOW
    -0.07
    æľ¬æĸĩ为
    -0.07
    æīij
    -0.07
    .cg
    -0.07
    fleisch
    -0.07
    zelt
    -0.07
    解åĨ³æĸ¹æ³ķ
    -0.07
    nga
    -0.07
    inga
    -0.07
    _keywords
    -0.07
    POSITIVE LOGITS
     separately
    0.08
    åIJĦèĩª
    0.08
     dominance
    0.08
    uvi
    0.07
     components
    0.07
     component
    0.07
    Domin
    0.07
    à¹ģà¸ķà¹Īละ
    0.07
    åįķçĭ¬
    0.07
    ãģĿãĤĮãģŀãĤĮ
    0.07
    Activations Density 0.004%

    No Known Activations