© 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. 48822
    Prev
    Next
    INDEX
    Explanations

    called or defined

    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
    ائØŃ
    -0.08
    erot
    -0.08
    ervo
    -0.08
    zea
    -0.08
    йда
    -0.08
    евна
    -0.07
    defer
    -0.07
    á»ıng
    -0.07
    ä¼ĺåĬ¿çļĦ
    -0.07
    .optional
    -0.07
    POSITIVE LOGITS
    å®ļä¹ī为
    0.09
     defined
    0.08
    æĮĩçļĦ
    0.08
    Ø¡
    0.08
     Defined
    0.07
     definition
    0.06
    å®ļ義
    0.06
     пÑĢизна
    0.06
    è¿ĺè´·
    0.06
    æĸĩä¸Ń
    0.06
    Activations Density 0.050%

    No Known Activations