© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    say "CSS"

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

    No Comments

    Negative Logits
     digital
    -53.25
    Digital
    -52.00
     Digital
    -51.25
     digit
    -50.00
    数字化
    -49.75
    digital
    -48.50
     Digit
    -48.25
    数字
    -47.50
    digit
    -45.75
     digits
    -45.00
    POSITIVE LOGITS
    CSS
    20.13
    Css
    17.63
     CSS
    17.38
    css
    16.38
    .css
    16.25
     css
    16.00
    _css
    16.00
    .CSS
    15.50
    (css
    15.50
    (Console
    14.00
    Activations Density 0.109%

    No Known Activations