© 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. 58084
    Prev
    Next
    INDEX
    Explanations

    XML/HTML tags and attributes

    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
    亲亲
    -0.08
    æĹłèĻij
    -0.08
    ry
    -0.07
    obo
    -0.07
     íĭ
    -0.07
    heber
    -0.07
    :disable
    -0.07
    ling
    -0.07
    ائÙĬ
    -0.07
     '//
    -0.07
    POSITIVE LOGITS
    çļĦ第ä¸Ģ个
    0.08
    第ä¸Ģç§į
    0.07
    å·¡
    0.07
    第ä¸Ģ个
    0.07
    第ä¸Ģ件äºĭ
    0.07
    第ä¸Ģä½į
    0.07
    ¬ģ
    0.07
    -cli
    0.07
    ä¼Ĭæĸ¯
    0.07
     ë²Ī째
    0.07
    Activations Density 0.007%

    No Known Activations