© 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. 604
    Prev
    Next
    INDEX
    Explanations

    programming languages and concepts

    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
    remark
    -0.08
    ä¿Ŀè¯ģäºĨ
    -0.07
     Mets
    -0.07
    maya
    -0.07
    åIJįåī¯åħ¶å®ŀ
    -0.07
    áž
    -0.07
    åı¯ä»¥ä¸º
    -0.07
    ricos
    -0.07
    Prime
    -0.07
    åħ³
    -0.07
    POSITIVE LOGITS
    ä»ĸ们ä¼ļ
    0.08
    åŃļ
    0.07
     rather
    0.07
    ä»ĸä»¬ä¹Ł
    0.07
    ä»ĸ们è¿ĺ
    0.07
    åĺ´è¾¹
    0.07
    åįĬ天
    0.07
    æĪĸèĢħæĺ¯
    0.07
    åĽłä¸ºä»ĸ们
    0.07
    inique
    0.07
    Activations Density 0.004%

    No Known Activations