© 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. 34969
    Prev
    Next
    INDEX
    Explanations

    etal sequences

    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
    æİ¢
    -0.07
    æı¡
    -0.07
    ero
    -0.06
    vog
    -0.06
    浸
    -0.06
    åĭ¿
    -0.06
    踩
    -0.06
    ly
    -0.06
    æĶ
    -0.06
    æľį
    -0.06
    POSITIVE LOGITS
    .compare
    0.08
    gadas
    0.08
    )::
    0.08
    okal
    0.07
    å¦Ĥçİī
    0.07
    ãģķãģĦ
    0.07
    Mixin
    0.07
    odb
    0.07
    tings
    0.07
    िश
    0.07
    Activations Density 0.010%

    No Known Activations