© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    say medical

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

    No Comments

    Negative Logits
    istical
    -18.25
     Mathematical
    -17.63
    透
    -16.88
     Perm
    -16.25
     Engineering
    -16.00
    paper
    -15.81
    _perm
    -15.81
    建设工程
    -15.75
    工程
    -15.75
     engineering
    -15.75
    POSITIVE LOGITS
    医
    60.50
     med
    57.00
    med
    51.00
    Med
    50.50
     Med
    48.75
     medic
    44.25
    .med
    43.25
    _med
    42.25
     medi
    41.25
    醫
    41.25
    Activations Density 0.040%

    No Known Activations