© 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. 63402
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    缼
    -0.08
    asiun
    -0.07
    .Encoding
    -0.07
    ,alpha
    -0.07
    gina
    -0.07
    enschaft
    -0.07
    áĥ§áĥĿ
    -0.07
    ingo
    -0.07
    rossover
    -0.07
    ÏĦον
    -0.07
    POSITIVE LOGITS
     кÑĢо
    0.06
     fak
    0.06
    èĦ
    0.06
     unt
    0.06
    缺ä¸Ģ
    0.06
    æĸ¹æ³ķä¸İ
    0.06
    æīĵä¸Ģ
    0.06
    åľ°ä¸İ
    0.06
    å°Ĩä¸İ
    0.06
    èĭ¦è¾£
    0.06
    Activations Density 0.002%

    No Known Activations