© 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. 59923
    Prev
    Next
    INDEX
    Explanations

    questions starting with is or does

    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
    usercontent
    -0.10
    æĪ´ç»´æĸ¯
    -0.09
    ccount
    -0.09
    ä¸ŃåĽ½ç«Ļ
    -0.08
    ÑĨÑĨа
    -0.08
    iverse
    -0.08
    ighborhood
    -0.08
    ulary
    -0.08
    鼷æĸ¯
    -0.08
    ήÏĦη
    -0.08
    POSITIVE LOGITS
    é»ĺ
    0.06
    âĢ
    0.06
    Âł
    0.05
    riez
    0.05
    Watcher
    0.05
    nici
    0.05
     _____
    0.05
    0.05
    ï¼İ
    0.05
     ↵
    0.05
    Activations Density 0.715%

    No Known Activations