© 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. 1319
    Prev
    Next
    INDEX
    Explanations

    [hospital] => [hospitalization]

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

    No Comments

    Negative Logits
     hospital
    -45.75
    医院
    -44.75
     hospitals
    -44.25
     Hospital
    -43.25
     Hospitals
    -40.75
    hospital
    -39.50
    醫院
    -38.50
    Hospital
    -37.50
    院
    -29.50
     hospitalized
    -28.50
    POSITIVE LOGITS
    RGBA
    17.13
    Sweden
    15.25
    lle
    14.69
    нов
    14.50
    Syntax
    14.38
     syntax
    14.31
     Beast
    14.25
    _syntax
    14.06
    pyx
    13.94
     SEXP
    13.94
    Activations Density 0.095%

    No Known Activations