© 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. 930
    Prev
    Next
    INDEX
    Explanations

    say "Indian"

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

    No Comments

    Negative Logits
    临港
    -22.50
     SAN
    -20.25
    珠海
    -20.13
    浦东
    -20.13
     Bahrain
    -20.00
    邺
    -20.00
    本市
    -19.63
    深圳市
    -19.50
     Napoli
    -19.25
     ε
    -19.13
    POSITIVE LOGITS
     Indian
    51.75
    Indian
    47.25
     Indians
    47.00
     indian
    39.75
     India
    37.25
    印度
    35.75
    India
    33.25
     Sioux
    32.50
     Cherokee
    32.25
     Native
    32.00
    Activations Density 0.795%

    No Known Activations