© 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. 410
    Prev
    Next
    INDEX
    Explanations

    say ancient Chinese figures

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

    No Comments

    Negative Logits
     Newfoundland
    -25.13
     Canadians
    -24.38
     Quebec
    -22.63
    赣州
    -22.00
    加拿
    -22.00
    加拿大
    -22.00
     Winnipeg
    -21.88
     Toronto
    -21.88
     Canadian
    -21.75
     Canada
    -21.50
    POSITIVE LOGITS
    老子
    34.50
    司马
    28.00
    秦
    23.50
    秦国
    23.38
    孔子
    20.38
    楚
    19.88
     Qin
    19.50
    芈
    18.75
    战国
    18.75
    桓
    18.50
    Activations Density 0.102%

    No Known Activations