© 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. 58930
    Prev
    Next
    INDEX
    Explanations

    URLs and technical terms

    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
    erville
    -0.07
    wür
    -0.07
    亨
    -0.07
    stvu
    -0.07
    ustom
    -0.06
     Tits
    -0.06
    enario
    -0.06
    stu
    -0.06
    èł
    -0.06
    uston
    -0.06
    POSITIVE LOGITS
    oire
    0.08
    à¸ī
    0.07
    Arte
    0.07
    beat
    0.07
    aho
    0.07
    ılı
    0.07
    å±ķå¼Ģåħ¨æĸĩ
    0.07
    rat
    0.07
    èĬ±èIJ½
    0.07
     beat
    0.07
    Activations Density 0.126%

    No Known Activations