© 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. 40691
    Prev
    Next
    INDEX
    Explanations

    java/object/library names

    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
    interes
    -0.08
    ivi
    -0.07
    ги
    -0.07
     outright
    -0.07
    arium
    -0.07
    çļĦèĥĮåIJİ
    -0.07
    ulare
    -0.07
    ulla
    -0.07
    баÑĢи
    -0.07
    çĶŁæł¹
    -0.07
    POSITIVE LOGITS
    rant
    0.07
    .util
    0.07
    leter
    0.07
     defaulted
    0.07
    _Default
    0.07
    åı£ä»¤
    0.06
    æIJ
    0.06
    ÏĢει
    0.06
    ä¹ĥèĩ³
    0.06
    ÛĮز
    0.06
    Activations Density 0.223%

    No Known Activations