© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    say "SQL columns"

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

    No Comments

    Negative Logits
     antenn
    -18.00
    细胞
    -17.88
    响应
    -17.63
    预测
    -17.38
     resposta
    -16.88
    vertices
    -16.88
    传统产业
    -16.88
     Gab
    -16.50
    predictions
    -16.50
     Vertex
    -16.38
    POSITIVE LOGITS
     columns
    17.38
     column
    17.00
    约束
    16.88
     TABLE
    15.50
     table
    15.25
     Column
    15.19
    _column
    15.13
    Column
    15.06
     comfort
    15.00
    Columns
    15.00
    Activations Density 0.138%

    No Known Activations