© 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. 59835
    Prev
    Next
    INDEX
    Explanations

    legends and myths

    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
    צ×ķ×¢
    -0.08
    оÑĢÑĤи
    -0.08
    reven
    -0.08
    uala
    -0.08
    ç½ijåıĭä¸Ĭä¼ł
    -0.08
    odega
    -0.08
    ç¤İ
    -0.07
    .ContentType
    -0.07
    trimmed
    -0.07
    odik
    -0.07
    POSITIVE LOGITS
    åIJį为
    0.13
    åIJįåı«
    0.12
    åı«åģļ
    0.12
    à¸Ħำวà¹Īา
    0.11
    åIJįåŃĹåı«
    0.11
     called
    0.11
    被称为
    0.11
    åı«
    0.10
    ä¸Ģ个åı«
    0.10
    æīĢè°ĵ
    0.10
    Activations Density 0.224%

    No Known Activations