© 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. 22823
    Prev
    Next
    INDEX
    Explanations

    function definition parameter

    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
    اذ
    -0.08
    ระ
    -0.08
    å¨Ł
    -0.07
    çݲçıij
    -0.07
    retch
    -0.06
     Zuk
    -0.06
    éķĩ人æ°ijæĶ¿åºľ
    -0.06
    -gnu
    -0.06
    ä¸ĸçķĮåIJĦåĽ½
    -0.06
    æľĪä¸Ĭ
    -0.06
    POSITIVE LOGITS
    éķľ
    0.08
    alang
    0.08
    mirror
    0.07
    unker
    0.07
     mir
    0.07
    esia
    0.07
     mirror
    0.07
    æĪĸ缴æİ¥
    0.07
    çľĭä¸Ĭåİ»
    0.07
    eshire
    0.07
    Activations Density 0.017%

    No Known Activations