© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 755
    Prev
    Next
    INDEX
    Explanations

    say "South Africa"

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

    No Comments

    Negative Logits
    常德
    -25.50
     Fuji
    -24.88
     Oregon
    -24.38
    Oregon
    -24.13
    Portland
    -24.00
     Mosul
    -23.63
    岳阳
    -23.63
     Istanbul
    -23.00
    洱
    -22.50
    昆明
    -22.00
    POSITIVE LOGITS
    南非
    52.00
     South
    50.00
    South
    46.50
     Johannesburg
    43.00
     apartheid
    39.50
     SA
    39.00
     SOUTH
    38.00
     Cape
    33.75
     Mandela
    33.25
    南
    33.00
    Activations Density 0.289%

    No Known Activations