© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    say "regex"

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

    No Comments

    Negative Logits
     mill
    -21.75
     Mill
    -21.50
    .segment
    -21.13
     segment
    -21.00
    segment
    -20.38
    _SEG
    -20.25
    seg
    -19.50
    (segment
    -19.38
    段
    -19.38
    Seg
    -19.38
    POSITIVE LOGITS
     regex
    25.25
    _hex
    22.38
     Hex
    22.38
    Regex
    22.00
     HEX
    21.75
    (regex
    21.50
    Hex
    21.50
    _regex
    21.38
    hex
    21.00
     Reflex
    20.88
    Activations Density 0.066%

    No Known Activations