© 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. 1464
    Prev
    Next
    INDEX
    Explanations

    say city

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

    No Comments

    Negative Logits
    城市
    -24.75
     cities
    -21.63
    的城市
    -21.00
    城市的
    -21.00
    城市发展
    -20.25
     urban
    -20.00
    城
    -19.88
    cities
    -19.75
     City
    -19.63
     city
    -19.50
    POSITIVE LOGITS
    语言
    17.13
    械
    16.25
    iban
    15.94
    語言
    15.69
    的语言
    15.50
    alph
    15.38
     Elf
    15.19
    𝛼
    14.75
    角
    14.69
    -alpha
    14.63
    Activations Density 0.155%

    No Known Activations