© 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. 15269
    Prev
    Next
    INDEX
    Explanations

    history, marital status, long duration

    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
    _named
    -0.07
    åĪĨ许
    -0.07
    edicine
    -0.07
    æ®ĸ
    -0.07
     rightfully
    -0.07
    广大人æ°ij群ä¼Ĺ
    -0.06
    ankind
    -0.06
     everywhere
    -0.06
    ä¸ĸçķĮåIJĦåľ°çļĦ
    -0.06
    çīĪæĿĥå±ŀäºİ
    -0.06
    POSITIVE LOGITS
    æĺ¯åIJ¦åľ¨
    0.09
    æĺ¯åIJ¦æĺ¯
    0.08
    æĺ¯åIJ¦ä¸º
    0.08
    æĺ¯åIJ¦æľī
    0.07
    è°
    0.07
     (\<
    0.07
    agne
    0.07
    æĺ¯åIJ¦
    0.07
    oup
    0.07
     subgroup
    0.07
    Activations Density 0.993%

    No Known Activations