© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    say Berkeley

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

    No Comments

    Negative Logits
     rep
    -18.25
    rep
    -17.88
     reps
    -16.38
    CW
    -16.25
    _rep
    -15.94
    Rep
    -15.69
    etsk
    -15.38
     petrol
    -14.88
    潍
    -14.81
     mật
    -14.75
    POSITIVE LOGITS
     Berkeley
    58.25
    Ber
    54.50
    伯
    53.25
     BER
    45.75
     Ber
    44.75
    BER
    43.50
     Berk
    43.25
    _ber
    40.25
     ber
    39.75
    ber
    39.25
    Activations Density 0.028%

    No Known Activations