© 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. 633
    Prev
    Next
    INDEX
    Explanations

    _MAJOR statistical references

    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
    æ¯ıæĹ¥ä¸Ģç»ĥ
    -0.08
    ä¼ł
    -0.07
    hal
    -0.07
    olest
    -0.07
    鲨
    -0.07
    Ðģ
    -0.07
    ä¸ĢæĹ¥
    -0.07
     Gür
    -0.07
    ä¸Ģ缴å¾Ī
    -0.06
    åIJĦæľīåIJĦ
    -0.06
    POSITIVE LOGITS
    entas
    0.07
    Ïīμα
    0.07
    zum
    0.07
    Opts
    0.07
    ova
    0.07
    istu
    0.07
    åıŃ
    0.06
    _MAJOR
    0.06
    å¥½åľ¨
    0.06
    ésil
    0.06
    Activations Density 0.431%

    No Known Activations