© 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. 56366
    Prev
    Next
    INDEX
    Explanations

    computational difficulty and bounds

    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
    åĴĮ好
    -0.07
    äºĭåıij
    -0.07
    OrDefault
    -0.07
    csr
    -0.07
    è²Į
    -0.07
    пон
    -0.07
    æľĢ大åĮĸ
    -0.07
    alte
    -0.06
    ansa
    -0.06
    å¼ı
    -0.06
    POSITIVE LOGITS
     DNC
    0.07
    åį³ä½¿æĺ¯
    0.07
     imposs
    0.07
    untas
    0.07
     freelancer
    0.07
    æĺ¯ä¸įåı¯
    0.07
    åį³ä½¿åľ¨
    0.07
    æīĽ
    0.07
    å¤įæĿĤ度
    0.07
    æĺ¯æĹłæ³ķ
    0.07
    Activations Density 0.012%

    No Known Activations