© 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. 987
    Prev
    Next
    INDEX
    Explanations

    say latin

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

    No Comments

    Negative Logits
     SX
    -22.13
    东莞
    -21.88
    SX
    -21.50
    鄠
    -21.13
    SV
    -21.13
    _sv
    -20.75
     Cv
    -20.75
    莞
    -20.63
     BX
    -20.38
     Sv
    -19.75
    POSITIVE LOGITS
    拉丁
    29.13
     Latin
    28.50
     latin
    25.88
     LATIN
    25.25
    Latin
    24.75
    美洲
    23.63
     latino
    22.00
     Americas
    20.75
    latin
    20.25
    Lat
    18.38
    Activations Density 0.363%

    No Known Activations