© 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. 19823
    Prev
    Next
    INDEX
    Explanations

    difficulties or problems

    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
    å®Ľ
    -0.07
    orz
    -0.07
    å¾Ĺæ°´
    -0.07
    åIJĦåĮº
    -0.07
    toc
    -0.07
    colar
    -0.07
    æľŃ
    -0.07
    éĢļè¿ĩè¿ĻäºĽ
    -0.07
    å°ıåı¶
    -0.07
     District
    -0.06
    POSITIVE LOGITS
    ãģĿãĤĤãģĿãĤĤ
    0.08
     trivial
    0.08
    æł¹æľ¬ä¸į
    0.08
    æĹ¢ä¸į
    0.08
    æł¹æľ¬å°±ä¸į
    0.08
    æĽ´ä¸įæĺ¯
    0.08
     irrelevant
    0.08
     neither
    0.08
     tampoco
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    Activations Density 0.003%

    No Known Activations