© 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. 64371
    Prev
    Next
    INDEX
    Explanations

    foreign words or character sequences

    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
    anghai
    -0.07
    à´Ļàµįà´Ļ
    -0.07
    åķŁ
    -0.07
    egur
    -0.07
    ä¹ĭéĹ´çļĦæĦŁæĥħ
    -0.07
    Executable
    -0.07
    ä¹ĭéĹ´çļĦçŁĽçĽ¾
    -0.07
    вÑĢо
    -0.06
    pell
    -0.06
    ä¸Ģå¼łå¼ł
    -0.06
    POSITIVE LOGITS
    icone
    0.08
    åIJĮæł·
    0.07
    vas
    0.07
    ieden
    0.07
    igen
    0.07
    ä¼ļåIJĮ
    0.06
    uge
    0.06
    imos
    0.06
    icon
    0.06
    rien
    0.06
    Activations Density 0.006%

    No Known Activations