© 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. 48600
    Prev
    Next
    INDEX
    Explanations

    unicode 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
    boh
    -0.07
    æĬĬä»ĸçļĦ
    -0.07
    amol
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    两次
    -0.07
    æĬĬéĴ±
    -0.07
    éħįæĪ´
    -0.07
    RTC
    -0.07
    Nil
    -0.07
    enske
    -0.07
    POSITIVE LOGITS
     Unicode
    0.11
     thousands
    0.08
    Unicode
    0.08
    æĺłå°Ħ
    0.07
    .overflow
    0.07
    .StatusCode
    0.07
    _range
    0.07
    èĮĥåĽ´
    0.07
    ANGER
    0.07
     диапаз
    0.07
    Activations Density 0.046%

    No Known Activations