© 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. 59991
    Prev
    Next
    INDEX
    Explanations

    “ followed by capitalized words

    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
    utton
    -0.08
    arella
    -0.07
     defaultManager
    -0.07
    鬼
    -0.06
    tails
    -0.06
    kent
    -0.06
    ë
    -0.06
     altrett
    -0.06
    hini
    -0.06
    ãĥĹãĥ«
    -0.06
    POSITIVE LOGITS
    æĸ¹æ³ķåıĬ
    0.08
     improved
    0.08
     purported
    0.08
    æĪijä¹Łæĺ¯
    0.07
    æĸ¹æ³ķåĴĮ
    0.07
    çİĭ建
    0.07
     ë°©ë²ķìĿ´
    0.07
    çļĦæĸ¹æ³ķåĴĮ
    0.07
    èĩ´åĬĽ
    0.07
    并æľī
    0.07
    Activations Density 0.627%

    No Known Activations