© 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. 44016
    Prev
    Next
    INDEX
    Explanations

    text separators and tables

    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
    erland
    -0.08
    åIJİèĥĮ
    -0.08
    好ä¸į
    -0.07
    <tool_response>
    -0.07
    iszt
    -0.07
    naver
    -0.07
    loquent
    -0.07
    hon
    -0.07
    ackage
    -0.06
    менование
    -0.06
    POSITIVE LOGITS
    西æĸ¯
    0.07
    被æī§è¡Į
    0.07
    áĢĽáĢ¾
    0.07
    weit
    0.06
    azzi
    0.06
    ás
    0.06
    績
    0.06
    çijļ
    0.06
    į
    0.06
    è¾ij
    0.06
    Activations Density 0.008%

    No Known Activations