© 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. 14477
    Prev
    Next
    INDEX
    Explanations

    say "at"

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

    No Comments

    Negative Logits
    igans
    -18.13
    ISC
    -17.75
    igan
    -17.50
     Hank
    -17.13
    rod
    -16.88
    getc
    -16.75
     Barcode
    -16.75
    ethylene
    -16.50
     ESC
    -16.38
    进博会
    -16.13
    POSITIVE LOGITS
    PAT
    21.63
     BAT
    20.38
    amat
    19.75
     Bath
    19.13
     flats
    18.88
    BAT
    18.63
    bat
    18.25
    prit
    17.38
    rit
    17.25
    atri
    17.25
    Activations Density 1.110%

    No Known Activations