© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14581
    Prev
    Next
    INDEX
    Explanations

    say "ar" suffix

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

    No Comments

    Negative Logits
    steen
    -21.75
    SX
    -20.25
    plen
    -20.00
    acen
    -19.50
     Staten
    -19.50
    weep
    -18.88
    斌
    -18.75
     McM
    -18.50
     SX
    -18.25
    sns
    -17.88
    POSITIVE LOGITS
    Ark
    20.13
    nar
    19.88
    marshaller
    19.13
    har
    19.00
     Ark
    18.63
    tar
    18.25
     HAR
    18.25
     zar
    18.13
    iar
    18.13
     mar
    18.13
    Activations Density 1.037%

    No Known Activations