© 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. 44369
    Prev
    Next
    INDEX
    Explanations

    correct location or order

    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
    lada
    -0.07
    pter
    -0.07
    |[
    -0.07
    æīĭå¿ĥ
    -0.06
    _EC
    -0.06
     tät
    -0.06
     variables
    -0.06
    æĶ¾ç¼ĵ
    -0.06
    èĮ¶æ±¤
    -0.06
    Ñİза
    -0.06
    POSITIVE LOGITS
    ä½įç½®
    0.09
    ä½įç½®çļĦ
    0.09
    认é¢Ĩ
    0.09
    éĶĻä½į
    0.09
    身份çļĦ
    0.09
     correctness
    0.09
     correct
    0.09
    _place
    0.08
    ä¸įåĬ¨
    0.08
    æŃ£ç¡®
    0.08
    Activations Density 0.011%

    No Known Activations