© 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. 51983
    Prev
    Next
    INDEX
    Explanations

    older participant, accessed microcomputer, calling party, occluding objects, late access, large table, visible file, effector cell, betrayed betrayer, parent child

    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
    ê²½
    -0.08
    åľ©
    -0.07
    öh
    -0.07
    交åĪ°
    -0.07
    дÑĢи
    -0.07
    avenport
    -0.07
    INES
    -0.07
    æ¯Ķä¸Ĭå¹´
    -0.07
     amateurs
    -0.06
    iong
    -0.06
    POSITIVE LOGITS
    çļĦä¸Ģæĸ¹
    0.08
    çļĦéĤ£ä¸ªäºº
    0.08
    ä¸Ģæĸ¹
    0.08
    /reference
    0.08
    lyn
    0.07
    ä¸Ģæĸ¹çļĦ
    0.07
    çļĦéĤ£ä¸ª
    0.07
     partner
    0.07
    åĴĮ缮æłĩ
    0.07
    å¥Ĺ
    0.07
    Activations Density 0.351%

    No Known Activations