© 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. 52124
    Prev
    Next
    INDEX
    Explanations

    held the, established by, disguise as, delegate to, filibuster

    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
    è¿Ļå°Ĩ
    -0.08
    ementer
    -0.08
    occan
    -0.08
    æĽ´åĬłå¼º
    -0.07
    天çĽĸ
    -0.07
    ontan
    -0.07
    _past
    -0.07
    对ä¸Ĭè¿°
    -0.07
    对è¿Ļ
    -0.07
    engang
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æĺ¯
    0.07
    U
    0.07
    åħ¶å®ŀæĺ¯
    0.07
     nowadays
    0.06
    0
    0.06
    æľīæŶåĢĻ
    0.06
    u
    0.06
    çļĦéĥ½æĺ¯
    0.06
    -ish
    0.06
    çļĦéĤ£ä¸ª
    0.06
    Activations Density 0.060%

    No Known Activations