© 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. 610
    Prev
    Next
    INDEX
    Explanations

    say "steel"

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

    No Comments

    Negative Logits
    肇庆
    -26.88
     Ecuador
    -24.88
    �
    -22.75
    清远
    -22.50
    茂名
    -22.38
    广东省
    -21.75
    江门
    -21.75
     df
    -21.75
     Cuba
    -21.38
    佛山
    -21.25
    POSITIVE LOGITS
     Pittsburgh
    48.25
     Steelers
    41.25
    鞍山
    38.25
     Carnegie
    31.75
    钢厂
    30.38
    沈阳
    30.13
    钢铁
    28.38
     Pitt
    28.00
    鞍
    26.00
    鲅
    25.75
    Activations Density 0.061%

    No Known Activations