© 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. 60077
    Prev
    Next
    INDEX
    Explanations

    injury and wounds

    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
    à§Ģয়
    -0.08
    çī¢çī¢æĬĬæı¡
    -0.08
    ÙĬاÙĨ
    -0.08
    èıĮ
    -0.07
    icrosoft
    -0.07
    欣欣
    -0.07
    éħµ
    -0.07
    ember
    -0.07
    æĹºçĽĽ
    -0.07
    unch
    -0.06
    POSITIVE LOGITS
     wounds
    0.12
     inflicted
    0.12
     injuries
    0.12
    伤çļĦ
    0.12
    æµģè¡Ģ
    0.12
    轻伤
    0.11
     injury
    0.11
    åıĹ伤
    0.11
    ãĤĴè²ł
    0.10
    累累
    0.10
    Activations Density 0.092%

    No Known Activations