© 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. 1113
    Prev
    Next
    INDEX
    Explanations

    say "Chinese provinces"

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

    No Comments

    Negative Logits
    广东
    -36.75
    广东省
    -33.25
    珠三角
    -30.63
    粤港澳
    -30.63
    岭南
    -28.88
    粤
    -27.50
    在广州
    -27.38
    华南
    -27.13
    广州
    -26.38
     Nigerian
    -25.75
    POSITIVE LOGITS
     Rocky
    16.13
     Omega
    15.75
    ω
    15.25
     Colorado
    15.25
     Olympia
    15.19
     Rockies
    14.94
     Loki
    14.69
    ATOM
    14.50
     omega
    14.19
    蒸汽
    14.19
    Activations Density 0.126%

    No Known Activations