© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    steam

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

    No Comments

    Negative Logits
    蒸汽
    -37.25
     steam
    -34.50
     Steam
    -32.25
    Steam
    -31.00
    steam
    -28.50
    蒸
    -25.00
     stream
    -24.88
     streams
    -23.25
     Vapor
    -23.00
     streamed
    -22.38
    POSITIVE LOGITS
    矩阵
    16.25
     canvas
    14.94
    canvas
    14.69
    antar
    14.63
     Canvas
    14.44
    料
    14.25
    _android
    14.19
     Angle
    14.13
    matrix
    13.94
    材料
    13.88
    Activations Density 0.058%

    No Known Activations