© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    [ country ] => Brazil

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

    No Comments

    Negative Logits
    拉丁
    -34.75
     Latin
    -33.50
    Latin
    -30.75
     latin
    -30.25
    latin
    -26.63
     Latino
    -24.00
     LATIN
    -23.25
    阿根廷
    -22.38
     latino
    -21.50
     Latina
    -20.38
    POSITIVE LOGITS
    公平
    17.63
    urger
    15.81
    lick
    15.50
    azen
    15.25
     fair
    15.25
     fairness
    15.00
    alink
    14.88
     brittle
    14.56
    URL
    14.50
    (styles
    14.44
    Activations Density 0.168%

    No Known Activations