© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    looks like or seems like

    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
    æķĻäºİ
    -0.07
    ron
    -0.07
    宣
    -0.07
    ort
    -0.07
    åįłåħ¨åĽ½
    -0.07
    绿åĮĸçİĩ
    -0.07
    _EN
    -0.07
     اÙĦض
    -0.07
    æĪijä¸įæĺ¯
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
    anding
    0.07
    nos
    0.07
    ulli
    0.07
    tant
    0.07
    ÑģÑĤоÑı
    0.07
    nor
    0.07
    éĮ¬
    0.07
    SKIP
    0.07
    说æĿ¥
    0.06
    ingan
    0.06
    Activations Density 0.002%

    No Known Activations