© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    say "Byzantine"

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

    No Comments

    Negative Logits
    遵义
    -21.75
    贵州省
    -21.75
    贵州
    -21.38
    贵阳
    -20.75
    仫
    -20.50
    重庆市
    -20.25
    阿根廷
    -19.75
     Bolivia
    -19.50
     Albuquerque
    -19.50
    涪
    -19.38
    POSITIVE LOGITS
     Byz
    37.75
    希腊
    32.75
    (ts
    32.75
     Constantin
    32.50
     ts
    32.00
     Bulgarian
    31.88
     Greek
    31.75
    _ts
    30.75
     κ
    30.63
    .ts
    30.25
    Activations Density 0.238%

    No Known Activations