© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3331
    Prev
    Next
    INDEX
    Explanations

    say "town"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    -component
    -21.13
     component
    -20.00
    	component
    -19.25
    组件
    -19.25
     Component
    -18.88
    (component
    -18.75
    元件
    -18.00
    Component
    -17.75
    component
    -17.38
    <Component
    -17.38
    POSITIVE LOGITS
     town
    67.00
    镇
    63.75
     Town
    60.75
    Town
    55.75
    全镇
    54.25
    鎮
    51.25
    town
    50.25
     towns
    48.50
    -town
    46.25
    镇政府
    45.75
    Activations Density 0.104%

    No Known Activations