© 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. 44815
    Prev
    Next
    INDEX
    Explanations

    see the or a

    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
    cdb
    -0.10
    ator
    -0.10
    è¡·å¿ĥçļĦ
    -0.09
     lá»ĵ
    -0.09
    paged
    -0.09
    jera
    -0.08
    ¶
    -0.08
    aires
    -0.08
    à¥ĩश
    -0.08
    äºĭå®ľ
    -0.08
    POSITIVE LOGITS
    /he
    0.10
    wards
    0.08
     firsthand
    0.08
    s
    0.08
    adows
    0.07
    aring
    0.07
    ings
    0.07
    çļĦæĺ¯ä¸Ģ个
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    端åĢª
    0.07
    Activations Density 0.120%

    No Known Activations