© 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. 2946
    Prev
    Next
    INDEX
    Explanations

    say "et"

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

    No Comments

    Negative Logits
    _pen
    -20.38
     PEN
    -20.00
    (Util
    -18.75
     Pen
    -18.75
     Util
    -17.75
    Pen
    -17.38
    灵
    -17.25
    怀
    -17.13
     pen
    -17.00
    pen
    -16.63
    POSITIVE LOGITS
    et
    27.00
    det
    25.38
    iset
    23.63
     det
    21.63
    .et
    20.63
    Det
    20.50
    ET
    19.88
    etten
    19.88
    (et
    19.25
    ett
    19.13
    Activations Density 0.136%

    No Known Activations