© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14997
    Prev
    Next
    INDEX
    Explanations

    indicates that or for

    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
    èĢħ们
    -0.07
    ebak
    -0.07
    ulut
    -0.06
     اÙĦÙĴÙħÙı
    -0.06
    åı«ä»Ģä¹Ī
    -0.06
    让åIJĮåѦ们
    -0.06
    åİļ
    -0.06
    à¥Į
    -0.06
    HTTPRequest
    -0.06
     Scr
    -0.06
    POSITIVE LOGITS
     antaranya
    0.08
    è¿Ľè¡Įä¸Ń
    0.07
    åIJĦç§įéĹ®é¢ĺ
    0.07
    åIJijæĹ¥
    0.07
    rav
    0.07
    fører
    0.07
    вода
    0.07
    /=
    0.07
    åIJijèį£
    0.06
    uncan
    0.06
    Activations Density 0.076%

    No Known Activations