© 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. 994
    Prev
    Next
    INDEX
    Explanations

    say Italian

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

    No Comments

    Negative Logits
    在北京
    -24.00
    在京
    -22.38
    在深圳
    -21.13
     Oakland
    -20.50
     Beijing
    -20.38
    北京市
    -19.63
    Oak
    -18.88
    在香港
    -18.50
     kok
    -17.88
     McKay
    -17.75
    POSITIVE LOGITS
    意大利
    28.38
    拉丁
    25.38
     Italia
    25.25
     Latin
    24.25
     Italian
    23.88
     Naples
    23.88
     LATIN
    23.13
     latin
    22.50
    Italian
    22.50
     Italy
    22.25
    Activations Density 0.148%

    No Known Activations