© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4917
    Prev
    Next
    INDEX
    Explanations

    acute lung injury

    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
    Negative Logits
    åĴĮåħ¶ä»ĸ
    -0.10
    åıĬåħ¶ä»ĸ
    -0.08
    åıĬ缸åħ³
    -0.08
    以åıĬåħ¶ä»ĸ
    -0.08
    èĢĮåħ¶ä»ĸ
    -0.07
    åĴĮ缸åħ³
    -0.07
    åĴĮåħ¶å®ĥ
    -0.07
    ä¸İåħ¶ä»ĸ
    -0.07
    æĸ¹æĸ¹éĿ¢
    -0.07
    禺
    -0.06
    POSITIVE LOGITS
    æĪĸ
    0.14
     or
    0.13
    -/
    0.12
    /
    0.12
    /or
    0.12
    หรืà¸Ń
    0.11
     или
    0.11
     Ø£ÙĪ
    0.11
    ãģ¾ãģŁãģ¯
    0.10
    åĴĮ
    0.10
    Activations Density 0.554%

    No Known Activations