© 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. 1732
    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
     garden
    -37.50
     gardens
    -37.00
    园
    -33.50
    花园
    -32.50
     Garden
    -31.00
     Gardens
    -29.88
     gardening
    -28.63
    园林
    -28.38
    園
    -27.63
     Garten
    -25.50
    POSITIVE LOGITS
     SQL
    20.63
    SQL
    20.00
    .SQL
    18.38
    /sql
    16.63
    物理
    16.13
    ssql
    15.94
     Microsoft
    15.88
    uvw
    15.44
    sql
    15.19
    ɛ
    15.13
    Activations Density 0.115%

    No Known Activations