© 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. 791
    Prev
    Next
    INDEX
    Explanations

    say US states

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

    No Comments

    Negative Logits
    成都
    -32.25
    成都市
    -32.25
    天府
    -31.13
    荥
    -28.00
    邛
    -28.00
     Tucson
    -26.13
    埃及
    -25.63
     sqlite
    -25.50
     SQLITE
    -25.25
     Cupertino
    -25.25
    POSITIVE LOGITS
     Dakota
    37.00
     Montana
    36.50
     Sioux
    36.00
     Saskatchewan
    33.50
     Minnesota
    33.00
     Iowa
    32.75
    沂
    32.75
    临沂
    32.25
     Nebraska
    31.50
    山东省
    31.50
    Activations Density 0.127%

    No Known Activations