© 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. 640
    Prev
    Next
    INDEX
    Explanations

    calculating differences

    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
    åįĬéĢĶ
    -0.08
    ä¸īé«ĺ
    -0.07
    akedown
    -0.07
    াহ
    -0.07
    ä¸īåı£
    -0.07
    èģĮä¸ļæĬĢæľ¯åŃ¦æł¡
    -0.07
    otá
    -0.07
    ä¸ĢåłĤ
    -0.07
    _AUX
    -0.07
    æİ¥æĽ¿
    -0.07
    POSITIVE LOGITS
     distance
    0.12
    -distance
    0.10
    distance
    0.10
    è·Ŀ离
    0.10
     Distance
    0.09
     distances
    0.09
    è·ĿéĽ¢
    0.09
     distanza
    0.09
    çļĦè·Ŀ离
    0.08
    Distance
    0.08
    Activations Density 0.151%

    No Known Activations