© 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. 17453
    Prev
    Next
    INDEX
    Explanations

    code variable names 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
    çī©è¯Ń
    -0.07
    REAM
    -0.07
    اصÙĦ
    -0.07
    ä½ĵ积å°ı
    -0.07
    adian
    -0.07
    åįıä¼ļä¼ļéķ¿
    -0.07
    urio
    -0.07
    udies
    -0.07
    ook
    -0.07
    egr
    -0.07
    POSITIVE LOGITS
     additional
    0.08
    éĻĦåĬł
    0.08
    ä¸Ģçľ¼
    0.07
    åĩij
    0.07
    æĭ§
    0.07
    ä¸Ģ并
    0.07
    é¢Ŀå¤ĸçļĦ
    0.07
    .additional
    0.07
    pter
    0.07
    æĪIJ份
    0.07
    Activations Density 0.038%

    No Known Activations