© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14406
    Prev
    Next
    INDEX
    Explanations

    say Korean

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

    No Comments

    Negative Logits
    XmlAttribute
    -17.63
    -horizontal
    -17.38
    -shell
    -16.75
    immel
    -16.63
    天鹅
    -16.50
    eldo
    -16.25
    xAF
    -15.94
    anders
    -15.69
    CAPE
    -15.50
    Caps
    -15.44
    POSITIVE LOGITS
     Korean
    27.38
     Korea
    27.00
    是韩国
    26.38
     Koreans
    25.63
    韓
    24.88
    韩国
    24.25
     Pyongyang
    23.50
    韩
    22.38
    朝鲜
    21.63
     Kore
    19.63
    Activations Density 0.139%

    No Known Activations