© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    say "script"

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

    No Comments

    Negative Logits
    Pok
    -17.75
     pok
    -17.38
    ông
    -17.38
    formula
    -17.13
    _formula
    -17.00
    念佛
    -16.38
     Islamic
    -16.38
     Joker
    -15.69
    牡丹
    -15.69
     MySQL
    -15.63
    POSITIVE LOGITS
     script
    20.50
     Script
    20.38
    Script
    20.00
     diagonal
    18.88
    音
    18.75
     Scripture
    18.38
    法国
    18.13
     french
    17.75
    语言
    17.63
    .ts
    17.50
    Activations Density 0.373%

    No Known Activations