© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    keywords and programming constructs

    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®ŀæĥħ
    -0.06
    ploy
    -0.06
    ány
    -0.06
    untut
    -0.06
    ngle
    -0.06
    ä¼¼çļĦ
    -0.06
    mouseleave
    -0.06
     Salute
    -0.06
    alse
    -0.05
    ALSE
    -0.05
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.08
     aforementioned
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.07
    omatis
    0.07
    aken
    0.07
    ServerError
    0.07
    arcz
    0.07
    ãĥ¬ãĤ¤
    0.07
    认è¯ģæĪIJåĬŁ
    0.07
    åIJĮæł·æĺ¯
    0.07
    Activations Density 0.219%

    No Known Activations