© 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. 31324
    Prev
    Next
    INDEX
    Explanations

    capitalized word after punctuation

    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
    asen
    -0.07
    rott
    -0.07
    iset
    -0.07
    ç¼ĺæķħ
    -0.07
    oa
    -0.07
    trup
    -0.07
    åĿIJ车
    -0.07
    olec
    -0.06
    asang
    -0.06
    led
    -0.06
    POSITIVE LOGITS
    eggio
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    jin
    0.07
     colorful
    0.07
    åı¤å±ĭ
    0.07
    iett
    0.06
    IALIZED
    0.06
    ä¸įåĪ°äºĨ
    0.06
     Kyl
    0.06
     HOLDER
    0.06
    Activations Density 0.006%

    No Known Activations