© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 479
    Prev
    Next
    INDEX
    Explanations

    say "Chinese Communist history"

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

    No Comments

    Negative Logits
    希腊
    -22.75
    bbc
    -21.25
     Baltimore
    -20.63
    鲅
    -20.38
     Baltic
    -20.25
     그리스
    -20.13
    (tc
    -20.00
     Athens
    -19.75
    滨州
    -19.75
    Κ
    -19.63
    POSITIVE LOGITS
    红军
    28.25
    赣
    24.63
    长征
    23.38
    毛泽东
    22.50
     Mao
    22.50
    延安
    22.00
    赣州
    20.75
    闽
    19.38
    毛泽
    19.00
    江西省
    19.00
    Activations Density 0.221%

    No Known Activations