© 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. 55151
    Prev
    Next
    INDEX
    Explanations

    invariant measure

    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
    agne
    -0.08
    agna
    -0.08
    sted
    -0.08
    _nsec
    -0.08
    apsed
    -0.08
    gether
    -0.08
     thá»į
    -0.07
    ehn
    -0.07
    ;base
    -0.07
    Ģ
    -0.07
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹Īåij¢
    0.10
    æĺ¯ä»Ģä¹Ī
    0.09
    à¸ļาà¸ĩà¸Ńยà¹Īาà¸ĩ
    0.07
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    0.07
    QG
    0.07
    iola
    0.07
     Inform
    0.07
    ä¸įåıĺçļĦ
    0.07
    ä¸įåıĺ
    0.06
    项
    0.06
    Activations Density 0.002%

    No Known Activations