© 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. 55273
    Prev
    Next
    INDEX
    Explanations

    circuit components and current

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èľ¡
    -0.08
    æĹłç¼Ŀ
    -0.07
     sheds
    -0.07
     SOAP
    -0.06
    SOAP
    -0.06
    离æĪij们
    -0.06
     transported
    -0.06
    EOF
    -0.06
    äºļåģ¥åº·
    -0.06
    念念ä¸įå¿ĺ
    -0.06
    POSITIVE LOGITS
    çļĦ设计
    0.09
    yel
    0.09
    æĺ¯çĶ¨æĿ¥
    0.09
    æĪĸ缴æİ¥
    0.09
    è¨Ńè¨Ī
    0.08
    istor
    0.08
     gánh
    0.08
    CurrentValue
    0.08
     terci
    0.08
    _bootstrap
    0.08
    Activations Density 0.026%

    No Known Activations