© 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. 904
    Prev
    Next
    INDEX
    Explanations

    say "ethnic groups"

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

    No Comments

    Negative Logits
    François
    -21.00
     france
    -19.50
     France
    -19.50
     Licence
    -19.13
    France
    -19.13
    ktor
    -18.13
     König
    -17.75
     Belgium
    -17.25
     Guil
    -17.25
     GER
    -16.75
    POSITIVE LOGITS
    加州
    30.88
    洛杉矶
    30.75
     Hawaiian
    30.38
     Californ
    28.88
     California
    28.13
    California
    26.88
     Hawaii
    26.00
     Latino
    25.63
    洛杉
    25.50
    在美国
    24.75
    Activations Density 0.152%

    No Known Activations