© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    say "culture"

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

    No Comments

    Negative Logits
     iron
    -38.75
     Iron
    -37.75
    铁
    -36.50
    钢铁
    -35.25
    Iron
    -35.00
    鐵
    -34.50
    IRON
    -31.13
    iron
    -29.75
    金属
    -29.50
     metal
    -29.13
    POSITIVE LOGITS
     culture
    23.75
    文化建设
    23.63
     tokens
    22.75
     Culture
    22.63
    _tokens
    21.75
     cultura
    21.63
    文化
    21.50
     token
    20.75
    Tokens
    20.75
     Muslim
    20.38
    Activations Density 0.096%

    No Known Activations