© 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. 30834
    Prev
    Next
    INDEX
    Explanations

    question starting words

    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
    uma
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    igue
    -0.07
    ocas
    -0.07
    æĹłåīį
    -0.07
    Sadly
    -0.07
    èĽĭ
    -0.07
     amat
    -0.06
    æ½ľ
    -0.06
    ä»ĸæĮĩåĩº
    -0.06
    POSITIVE LOGITS
     whether
    0.10
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
    æĺ¯åIJ¦æľī
    0.09
    æľī没æľī
    0.09
    æĺ¯ä¸įæĺ¯
    0.09
     apakah
    0.08
    æĺ¯åIJ¦
    0.08
     Whether
    0.08
    æĺ¯åIJ¦åľ¨
    0.08
    æĺ¯åIJ¦ä¸İ
    0.08
    Activations Density 0.022%

    No Known Activations