© 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. 44923
    Prev
    Next
    INDEX
    Explanations

    include file, render page

    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
    arre
    -0.08
    ctors
    -0.07
    anche
    -0.07
    åıĮé¾Ļ
    -0.07
    gesi
    -0.07
    è¯ŀè¾°
    -0.06
    kola
    -0.06
    ário
    -0.06
    ários
    -0.06
    ungi
    -0.06
    POSITIVE LOGITS
    ItemList
    0.07
    å¾·ç½Ĺ
    0.07
    éĿĴ天
    0.07
    éľ
    0.06
    ConfigureAwait
    0.06
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.06
    ugas
    0.06
    äºij天
    0.06
    itelist
    0.06
    bidden
    0.06
    Activations Density 0.091%

    No Known Activations