© 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. 14481
    Prev
    Next
    INDEX
    Explanations

    say ordinal suffixes

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

    No Comments

    Negative Logits
     advertisement
    -19.50
    рид
    -19.13
     ad
    -18.25
    erd
    -18.25
    垫
    -17.88
    广告
    -17.88
    氡
    -17.75
    дер
    -17.13
     Adler
    -17.00
     Indy
    -16.88
    POSITIVE LOGITS
    瓜
    19.00
    yu
    17.00
    quina
    16.00
    llu
    16.00
    tk
    15.69
    okus
    15.56
    tt
    15.25
    trx
    15.06
    tx
    15.00
    ttl
    15.00
    Activations Density 0.055%

    No Known Activations