© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    say Chinese political names

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

    No Comments

    Negative Logits
     vampires
    -20.75
    海盗
    -20.38
     pirate
    -20.00
    IPA
    -19.88
     pirates
    -19.63
    BOT
    -19.50
    希腊
    -19.38
    spotify
    -19.00
     BOT
    -19.00
    Uber
    -19.00
    POSITIVE LOGITS
     Mao
    38.00
     Beijing
    33.75
     Shanghai
    31.75
     Yang
    30.38
    毛泽东
    30.13
     Chinese
    29.63
    延安
    28.00
    周恩来
    27.88
     Jiang
    27.63
     Zhou
    27.38
    Activations Density 0.433%

    No Known Activations