© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    medical

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

    No Comments

    Negative Logits
     medical
    -55.75
     Medical
    -52.50
    Medical
    -50.75
    medical
    -50.00
    医疗
    -49.00
    医学
    -46.25
     medically
    -41.50
     меди
    -41.00
     MED
    -39.50
    -med
    -38.25
    POSITIVE LOGITS
    .RGB
    17.13
    Pixels
    14.50
     Gunn
    14.25
    matrix
    13.94
    EU
    13.63
    auer
    13.44
    Ψ
    13.44
    heet
    13.44
    eea
    13.25
    psi
    13.19
    Activations Density 0.155%

    No Known Activations