© 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. 964
    Prev
    Next
    INDEX
    Explanations

    say bean

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

    No Comments

    Negative Logits
    武汉市
    -31.25
    武汉
    -27.25
    宜昌
    -25.88
    湖北省
    -25.25
     Irish
    -24.63
     Prague
    -24.50
    爱尔兰
    -24.50
     Dublin
    -23.75
     Ireland
    -23.63
    十堰
    -23.63
    POSITIVE LOGITS
     bean
    54.50
    豆
    53.00
     Bean
    51.25
    Bean
    49.75
     beans
    49.50
    bean
    48.00
    大豆
    46.50
     soy
    45.00
    (bean
    44.00
     Beans
    43.50
    Activations Density 0.133%

    No Known Activations