© 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. 44339
    Prev
    Next
    INDEX
    Explanations

    math symbols or code constructs

    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
    ondo
    -0.08
    对ç¾İåĽ½
    -0.08
    /Branch
    -0.08
    对åŃ¦æł¡
    -0.08
    å«£çĦ¶
    -0.07
    agno
    -0.07
    å¼ĢéĹ¨çº¢
    -0.07
    åĸ³åĸ³
    -0.07
    çī¢
    -0.07
    uvo
    -0.07
    POSITIVE LOGITS
    ÑĮе
    0.07
    åĭŁéĽĨ
    0.06
    å°Ĩä»ĸ
    0.06
    indr
    0.06
    æĩ
    0.06
    fum
    0.06
    æĮºèº«
    0.06
    iere
    0.06
    ä½Ļ
    0.06
    身
    0.06
    Activations Density 0.001%

    No Known Activations