© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2864
    Prev
    Next
    INDEX
    Explanations

    say "伯"

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

    No Comments

    Negative Logits
    有色
    -14.88
     Evans
    -14.00
     Gen
    -13.88
    рю
    -13.75
    Gen
    -13.69
     Patt
    -13.56
     Fem
    -13.50
    十万
    -13.44
    uling
    -13.13
     wedge
    -13.13
    POSITIVE LOGITS
    伯
    78.00
     Ber
    66.50
    Ber
    65.50
     ber
    58.50
     BER
    56.75
    ber
    55.75
    _ber
    52.00
    BER
    50.75
     Bern
    47.50
     mer
    45.50
    Activations Density 0.047%

    No Known Activations