© 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. 14445
    Prev
    Next
    INDEX
    Explanations

    Chinese surnames

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

    No Comments

    Negative Logits
    ersed
    -16.00
     spoiled
    -15.56
    nyder
    -15.31
     Anders
    -14.88
    odesk
    -14.63
    nee
    -14.50
    chter
    -14.00
    鹬
    -14.00
    风光
    -14.00
    ˌ
    -13.94
    POSITIVE LOGITS
    囊
    18.38
     bras
    17.38
    ramid
    17.25
     Rath
    17.00
     Citizen
    17.00
    lob
    16.63
    pl
    16.25
     Stem
    16.25
    aim
    16.00
    pla
    16.00
    Activations Density 1.248%

    No Known Activations