© 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. 34751
    Prev
    Next
    INDEX
    Explanations

    function, session, form, scene

    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
    éķ¿åħ´
    -0.07
    ardini
    -0.07
    ond
    -0.07
    untas
    -0.07
    und
    -0.07
    epar
    -0.07
    ä¹ĭåIJİåĨį
    -0.07
     Manfred
    -0.07
    unut
    -0.06
    мени
    -0.06
    POSITIVE LOGITS
    åIJ¦
    0.07
    å°Ŀ
    0.07
    ods
    0.07
    unker
    0.07
    ắng
    0.07
    tiv
    0.07
    æĪIJè´¥
    0.07
    bower
    0.07
    èĢ³è¾¹
    0.07
    å®ģ
    0.07
    Activations Density 0.023%

    No Known Activations