© 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. 61538
    Prev
    Next
    INDEX
    Explanations

    scarcity or unavailability

    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
    åŁºä¸ļ
    -0.08
    交åºķ
    -0.07
    _suite
    -0.07
     abd
    -0.07
    ä¸į离
    -0.07
    wab
    -0.07
    夷
    -0.07
    gee
    -0.07
    IFT
    -0.07
    ç²Ĺå¿ĥ
    -0.07
    POSITIVE LOGITS
    æĭ¥æĮ¤
    0.14
    æĮ¤
    0.13
     overcrow
    0.12
    ä¾Ľä¸įåºĶæ±Ĥ
    0.12
     availability
    0.12
     congestion
    0.12
     crowded
    0.12
    容éĩı
    0.12
    容éĩıçļĦ
    0.12
    æİĴéĺŁ
    0.12
    Activations Density 0.213%

    No Known Activations