© 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. 42461
    Prev
    Next
    INDEX
    Explanations

    with property, with jumps, with periodic, with long, with short

    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
    [value
    -0.07
    ä¸īéĢļ
    -0.07
    Nature
    -0.07
    erbe
    -0.06
    请åIJĦä½į
    -0.06
    åħ±æµİ
    -0.06
    ãģ¾ãģ¾
    -0.06
    ãĥªãĥ¼ãĥ³
    -0.06
    æį»
    -0.06
    inou
    -0.06
    POSITIVE LOGITS
    æĮĩå®ļ
    0.08
    ucht
    0.07
    ddit
    0.07
    éªĩ
    0.07
    "](
    0.07
    ujet
    0.07
     sole
    0.07
    íĸ¥
    0.07
    度éĩı
    0.07
    ÙĬرÙĩ
    0.07
    Activations Density 0.263%

    No Known Activations