© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    say "country names"

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

    No Comments

    Negative Logits
     Canada
    -35.00
    Canada
    -30.38
    加拿大
    -26.63
     Canadian
    -26.38
    加拿
    -25.88
     canvas
    -25.75
    canvas
    -25.38
    Canvas
    -25.00
     Canvas
    -24.50
    Canadian
    -24.13
    POSITIVE LOGITS
    Algorithm
    18.00
    algorithm
    17.88
     athlete
    17.75
     Algorithms
    16.88
     allele
    16.38
    武功
    16.25
     algorithm
    16.25
     technology
    15.94
    technology
    15.81
     Algorithm
    15.75
    Activations Density 0.077%

    No Known Activations