© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49389
    Prev
    Next
    INDEX
    Explanations

    line search or battle line

    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
    å¦į
    -0.08
    antie
    -0.07
    à¸ĸม
    -0.07
    ussin
    -0.07
    utherland
    -0.07
    åŃ¦å·¥
    -0.07
    umpf
    -0.07
    Computed
    -0.07
    anten
    -0.07
    HEN
    -0.07
    POSITIVE LOGITS
     Bott
    0.08
    继ç»Ńè¿Ľè¡Į
    0.07
     House
    0.07
    sched
    0.07
    ä¸įèĻļ
    0.06
    /new
    0.06
    atab
    0.06
     chosen
    0.06
     pivot
    0.06
     Auction
    0.06
    Activations Density 0.001%

    No Known Activations