© 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. 944
    Prev
    Next
    INDEX
    Explanations

    say "Qing dynasty"

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

    No Comments

    Negative Logits
    MLS
    -22.50
     ML
    -22.25
    WF
    -21.38
     MLS
    -21.13
     WF
    -20.38
    橄榄
    -19.00
    芝加哥
    -18.88
     WP
    -18.75
     Toledo
    -18.25
     DW
    -18.13
    POSITIVE LOGITS
    康熙
    40.00
    乾隆
    33.00
    在北京
    30.38
     Beijing
    30.13
    清朝
    30.00
     Qing
    29.38
     Tibet
    26.75
    胤
    26.63
     Mongolia
    26.00
    Hong
    24.88
    Activations Density 0.265%

    No Known Activations