© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1361
    Prev
    Next
    INDEX
    Explanations

    say "medical terms"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     injury
    -31.38
    伤
    -29.38
     injuries
    -27.50
    受伤
    -26.88
     Injury
    -26.38
    损伤
    -25.50
     engineering
    -25.25
     injured
    -25.00
    傷
    -24.63
    工程
    -24.25
    POSITIVE LOGITS
     Mac
    22.50
    Mac
    22.13
     MAC
    19.63
     Git
    19.63
     mac
    19.25
    云计算
    18.25
    _mac
    17.75
    MAC
    17.63
    算法
    17.50
    Git
    17.38
    Activations Density 0.150%

    No Known Activations