© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ì§ĢëĭĪìĸ´
    -0.08
    ä¸ĵä¸ļåĴĮ
    -0.07
    दà¥Ģ
    -0.07
     both
    -0.07
    <quote
    -0.06
     ê·¸ë¦¬ê³ł
    -0.06
    both
    -0.06
    åĴĮåľ¨
    -0.06
    åĽ¾çīĩåĴĮ
    -0.06
     hins
    -0.06
    POSITIVE LOGITS
     or
    0.29
    æĪĸ
    0.28
    æĪĸèĢħ
    0.28
    æĢ§æĪĸ
    0.28
     или
    0.27
     hoặc
    0.27
     atau
    0.27
     oder
    0.27
     vagy
    0.26
    æĪĸèĢħæĺ¯
    0.26
    Activations Density 0.609%

    No Known Activations