© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15595
    Prev
    Next
    INDEX
    Explanations

    say EU

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

    No Comments

    Negative Logits
    美国人
    -18.75
    在美国
    -18.63
    亿美元
    -18.63
    美军
    -18.25
     amer
    -17.25
    美国
    -16.25
    秃
    -16.13
     Raiders
    -15.94
     Americans
    -15.44
     Amer
    -15.13
    POSITIVE LOGITS
     Eu
    32.00
    Eu
    30.63
     European
    30.00
    欧洲
    28.88
     EU
    28.38
     européen
    28.25
    European
    27.88
     eu
    27.75
     Europe
    27.50
    EU
    27.50
    Activations Density 0.275%

    No Known Activations