© 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. 43704
    Prev
    Next
    INDEX
    Explanations

    element or property access

    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
    ç¯Ŀ
    -0.07
    çļĦä¸Ģ项æĺ¯
    -0.07
    ÑĢина
    -0.07
     (_,
    -0.07
    "":
    -0.07
    riz
    -0.07
    '))->
    -0.06
     inilah
    -0.06
    regular
    -0.06
    :;"
    -0.06
    POSITIVE LOGITS
    ovel
    0.07
    azol
    0.07
    åĽłä¸ºå®ĥ们
    0.07
    Ïĩη
    0.07
    ewise
    0.07
    zez
    0.07
    iseurs
    0.07
    åįķä½įåıĤåĬł
    0.07
    .encode
    0.07
    eselect
    0.07
    Activations Density 0.055%

    No Known Activations