© 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. 719
    Prev
    Next
    INDEX
    Explanations

    say "NASA"

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

    No Comments

    Negative Logits
     Norway
    -22.38
    挪威
    -22.38
    闽
    -22.38
    .nz
    -22.00
     Malay
    -21.63
     Malta
    -21.50
     Danish
    -21.50
     NZ
    -21.38
    新西兰
    -21.25
    瑞典
    -21.25
    POSITIVE LOGITS
     NASA
    30.75
    NASA
    30.38
    华盛顿
    27.88
    白宫
    26.38
     Nixon
    25.63
     Houston
    24.63
     Washington
    24.63
     Ames
    23.88
     CIA
    23.25
    拜登
    23.00
    Activations Density 0.142%

    No Known Activations