© 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. 903
    Prev
    Next
    INDEX
    Explanations

    say "Maya"

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

    No Comments

    Negative Logits
     Icelandic
    -25.50
    挪威
    -23.75
    瑞典
    -23.38
    荷兰
    -23.00
    无锡
    -22.25
     Iceland
    -22.13
     Norwegian
    -21.88
    张家口
    -21.75
    Rails
    -21.25
     Swedish
    -21.13
    POSITIVE LOGITS
     Maya
    18.50
     mx
    18.50
     ceremonial
    17.50
    (mx
    17.38
    Az
    17.38
     MX
    17.38
    mx
    16.75
     pottery
    16.75
     AZ
    16.38
    .mx
    16.38
    Activations Density 0.104%

    No Known Activations