© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    medicine

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

    No Comments

    Negative Logits
    Med
    -50.75
     med
    -50.50
     medicine
    -48.25
     Med
    -47.25
     Medicine
    -46.25
    med
    -46.00
     MED
    -46.00
    medicine
    -44.25
    _med
    -43.25
     méd
    -40.50
    POSITIVE LOGITS
     graph
    13.88
    설
    13.56
    -di
    13.50
    Brazil
    13.44
     culpa
    13.38
    �
    13.31
     guilty
    13.25
     Satan
    13.25
    	graph
    13.06
    축
    12.81
    Activations Density 0.065%

    No Known Activations