© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    say "SQL"

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

    No Comments

    Negative Logits
    矩阵
    -55.50
     matrix
    -54.75
     matrices
    -51.50
    matrix
    -48.25
     Matrix
    -47.50
     Mat
    -47.25
     mat
    -47.00
     MATRIX
    -46.00
    Mat
    -45.75
    _mat
    -44.75
    POSITIVE LOGITS
    SQL
    15.38
    Sql
    14.31
    _race
    14.25
    工具
    14.00
    .SQL
    14.00
     Hispan
    14.00
     SQL
    13.88
    _sql
    13.81
    emic
    13.31
    航海
    13.31
    Activations Density 0.086%

    No Known Activations