© 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. 37519
    Prev
    Next
    INDEX
    Explanations

    scientific research findings

    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
    æ¡ĵ
    -0.07
    uary
    -0.07
     statist
    -0.07
    ç»Łè®¡è¡¨
    -0.07
    Stats
    -0.07
    ç»Łè®¡
    -0.07
    Statistic
    -0.07
     statistic
    -0.06
    .statistics
    -0.06
    rau
    -0.06
    POSITIVE LOGITS
     molecular
    0.11
     cloned
    0.11
     cloning
    0.10
     assays
    0.10
     mechan
    0.10
     linker
    0.10
     genome
    0.10
     implicated
    0.10
     biochemical
    0.10
     metallo
    0.09
    Activations Density 1.463%

    No Known Activations