© 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. 661
    Prev
    Next
    INDEX
    Explanations

    say sigma

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

    No Comments

    Negative Logits
    宜昌
    -45.50
     Lahore
    -42.00
     Czech
    -41.00
    湖北省
    -41.00
    武汉
    -40.75
     Prague
    -40.75
    银川
    -39.50
    武汉市
    -38.75
    郧
    -38.25
    十堰
    -37.25
    POSITIVE LOGITS
     σ
    22.63
    (sigma
    22.25
    σ
    22.00
    (gp
    21.75
    大豆
    21.38
     gp
    21.13
    sigma
    20.25
    橡胶
    19.88
     sigma
    19.75
     Gaussian
    19.25
    Activations Density 0.450%

    No Known Activations