© 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. 2665
    Prev
    Next
    INDEX
    Explanations

    say "digit"

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

    No Comments

    Negative Logits
    (et
    -21.13
    套
    -20.38
     et
    -18.25
     reflection
    -18.13
     reflect
    -17.88
    條
    -17.75
    reflect
    -17.63
    (ret
    -17.38
    reflection
    -17.38
     ET
    -17.13
    POSITIVE LOGITS
     digit
    26.25
    Digit
    24.88
     Digit
    24.25
    digit
    23.50
     digits
    22.63
    辨
    20.63
    cert
    20.25
    _digit
    20.00
    数字化
    19.75
    -digit
    19.63
    Activations Density 0.055%

    No Known Activations