© 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. 49134
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or context

    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
    ynu
    -0.07
    pite
    -0.07
    第ä¸Ģç¯ĩ
    -0.07
    ода
    -0.07
    inius
    -0.06
    é¡ķ
    -0.06
    ä¸įæ¯Ķ
    -0.06
    /welcome
    -0.06
    ãĥIJãĥ©
    -0.06
    第ä¸ĢåIJį
    -0.06
    POSITIVE LOGITS
    others
    0.08
     otherwise
    0.07
    ÑĢг
    0.07
     others
    0.07
    _SENT
    0.06
    è¡ĮåĪĹ
    0.06
     bunch
    0.06
    ipher
    0.06
    abouts
    0.06
    Trou
    0.06
    Activations Density 0.302%

    No Known Activations