© 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. 24398
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols

    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
     nob
    -0.07
    设置
    -0.06
    çĽĺé¾Ļ
    -0.06
    еÑĩе
    -0.06
    ERC
    -0.06
    åĩłä¸ª
    -0.06
    ä¸ĢçĽ´ä»¥
    -0.06
    ç»Ŀèī²
    -0.06
    gov
    -0.06
    lech
    -0.06
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.08
     belonging
    0.08
    xCD
    0.08
     darin
    0.08
    æĿ¥èĩª
    0.08
     therein
    0.08
    åĿĩæĿ¥èĩª
    0.08
    é»Ħç´ł
    0.08
     provenant
    0.08
     belongs
    0.07
    Activations Density 0.021%

    No Known Activations