© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15532
    Prev
    Next
    INDEX
    Explanations

    say "ar" words

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

    No Comments

    Negative Logits
     Chelsea
    -26.63
    Chelsea
    -24.38
     Vega
    -20.63
     CPL
    -20.50
    啤酒
    -20.13
    ETF
    -19.88
    濂
    -19.13
    淠
    -18.63
    河西
    -18.13
    QE
    -18.00
    POSITIVE LOGITS
    ar
    44.25
    ар
    41.50
    -ar
    41.25
     ar
    41.00
    AR
    40.75
    ars
    40.25
    aris
    40.00
    arb
    39.75
    ARS
    39.25
    (ar
    39.25
    Activations Density 7.772%

    No Known Activations