© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21880
    Prev
    Next
    INDEX
    Explanations

    states or conditions occurring unexpectedly

    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
    allback
    -0.08
    éķIJ
    -0.08
    尼迪
    -0.08
    zgl
    -0.07
    ostro
    -0.07
    _DECLARE
    -0.07
    lena
    -0.07
    ugins
    -0.07
    æĢ»æİĴåIJį
    -0.07
    ow
    -0.07
    POSITIVE LOGITS
    çİĩåħĪ
    0.09
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    åIJĮæŃ¥
    0.07
    å·¥ä½ľçļĦåIJĮæŶ
    0.07
     independently
    0.07
    ä¸ĢåIJĮ
    0.07
    åıĹåĪ°å½±åĵį
    0.07
    ä¸Ģ并
    0.07
    åıĹå½±åĵį
    0.06
    çļĦåıĺåĮĸ
    0.06
    Activations Density 0.324%

    No Known Activations