© 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. 2797
    Prev
    Next
    INDEX
    Explanations

    say "fmt"

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

    No Comments

    Negative Logits
     capital
    -20.88
     Capital
    -19.25
    .cap
    -18.88
     CAPITAL
    -18.63
    .�
    -18.38
    Capital
    -18.00
    (cap
    -17.75
     cap
    -17.75
    .Cap
    -17.50
    资本
    -17.38
    POSITIVE LOGITS
     Fac
    35.25
    Fac
    34.50
    _fac
    33.00
     Facility
    31.63
    fac
    31.63
     facility
    31.38
    .fac
    29.13
     fmt
    28.88
    facility
    27.88
     facilities
    27.50
    Activations Density 0.134%

    No Known Activations