© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1917
    Prev
    Next
    INDEX
    Explanations

    city, news, online, roads, deep

    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
    ...
    -0.06
    âĢ¦
    -0.06
    -
    -0.06
    辺
    -0.06
    æģIJ
    -0.05
    Å¡
    -0.05
    *
    -0.05
    æĪĴ
    -0.05
    ä¸įæĺ¯åľ¨
    -0.05
    '
    -0.05
    POSITIVE LOGITS
    è¿ĶåĽŀ顶éĥ¨
    0.10
     zaws
    0.08
    ä¸ĵ家认为
    0.08
    æľĢæĸ°æĸĩç«ł
    0.08
     bạ
    0.08
    ä¸ĵ家表示
    0.08
    serter
    0.08
    ç½Ĺæĸ¯
    0.08
    ://%
    0.08
    尾声
    0.08
    Activations Density 0.054%

    No Known Activations