© 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. 941
    Prev
    Next
    INDEX
    Explanations

    say "SQL terms"

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

    No Comments

    Negative Logits
    .telegram
    -18.63
     Telegram
    -18.63
    Telegram
    -18.50
    instagram
    -18.25
     gtk
    -17.63
    彝
    -17.50
    	gtk
    -17.25
     Brigham
    -17.13
    砟
    -16.75
    clave
    -16.63
    POSITIVE LOGITS
    SqlParameter
    17.75
     MSD
    17.13
     SAS
    17.00
     SST
    16.25
     SQL
    16.13
     MSS
    16.13
    (SS
    15.88
     SS
    15.81
    SQL
    15.81
     pubs
    15.00
    Activations Density 0.068%

    No Known Activations