© 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. 4572
    Prev
    Next
    INDEX
    Explanations

    not to make

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èµ°å¼±
    -0.08
    uarios
    -0.08
    走强
    -0.08
    vrier
    -0.08
    ellini
    -0.08
    ä»Ĭå¤ľ
    -0.08
    HING
    -0.07
    个个
    -0.07
    alytics
    -0.07
     <![
    -0.07
    POSITIVE LOGITS
    娥
    0.08
    çijŁ
    0.08
    æ¢ĵ
    0.08
    å¿łäºİ
    0.07
     contextual
    0.07
    ÙĦÙĪب
    0.07
    è¯ļå®ŀå®Īä¿¡
    0.07
     padi
    0.07
    å¹½é»ĺ
    0.07
    çijķ
    0.07
    Activations Density 0.004%

    No Known Activations