© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    临床

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

    No Comments

    Negative Logits
     clinical
    -45.00
    临床
    -44.50
     Clinical
    -42.50
    Clinical
    -42.50
    clinical
    -35.75
     clinically
    -32.25
     Clin
    -24.00
     clin
    -22.75
     clinicians
    -21.63
     кли
    -21.13
    POSITIVE LOGITS
     Mus
    17.25
    socket
    16.38
     Sym
    16.13
     Oil
    15.75
    _sym
    15.69
    arden
    15.63
     µ
    15.63
     Math
    15.63
     mus
    15.63
    porte
    15.50
    Activations Density 0.097%

    No Known Activations