© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    spherical shapes and associated concepts

    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
    <|box_end|>
    -0.12
    ами
    -0.10
    tures
    -0.10
    -même
    -0.09
    fully
    -0.09
    eita
    -0.09
    lessly
    -0.09
    yczy
    -0.09
    jenigen
    -0.09
    queur
    -0.09
    POSITIVE LOGITS
    s
    0.10
    Ùĩ
    0.10
    ãĥ³
    0.08
    sburg
    0.08
    -
    0.08
    /or
    0.08
    åľ¨
    0.07
    ات
    0.07
    ãģĦãĤĭ
    0.07
     Ganze
    0.07
    Activations Density 0.003%

    No Known Activations