© 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. 45304
    Prev
    Next
    INDEX
    Explanations

    sample and question processing

    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¡
    -0.07
    illin
    -0.07
    OwnProperty
    -0.07
    iya
    -0.07
    鸾
    -0.06
    ÐŁÐ¸
    -0.06
    (exports
    -0.06
     Samstag
    -0.06
    <decltype
    -0.06
    andbox
    -0.06
    POSITIVE LOGITS
    æľīæĿĥ
    0.08
     iter
    0.08
     processed
    0.07
    æݥ踵
    0.07
     Wes
    0.07
     оÑĩеÑĢед
    0.07
    串è¡Į
    0.07
    sequential
    0.07
     Kooper
    0.07
     Sequential
    0.07
    Activations Density 0.024%

    No Known Activations