© 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. 33800
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
    缮ä¸Ń
    -0.06
    awas
    -0.06
    ans
    -0.06
     lore
    -0.06
     dụ
    -0.06
    awa
    -0.06
    anden
    -0.06
    à¹ĥหà¹īà¸Ļำ
    -0.06
    chein
    -0.06
    交æīĢ
    -0.06
    POSITIVE LOGITS
     whenever
    0.08
     Whenever
    0.08
     seme
    0.08
    ï¸İ
    0.08
    _nullable
    0.07
    ä¸ĢäºĽçļĦ
    0.07
    bnb
    0.07
    åĩ¡
    0.07
    çar
    0.07
    acre
    0.07
    Activations Density 0.030%

    No Known Activations