© 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. 2976
    Prev
    Next
    INDEX
    Explanations

    say "emp" words

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

    No Comments

    Negative Logits
     Et
    -21.75
    Et
    -21.25
    (et
    -21.00
     et
    -20.25
    _et
    -19.50
    .et
    -17.88
    -et
    -17.38
    et
    -17.13
    etas
    -16.75
    丙
    -16.25
    POSITIVE LOGITS
    emp
    49.50
     emp
    49.00
     Emp
    48.75
    (emp
    46.50
    Emp
    46.50
    .emp
    42.25
    _emp
    40.50
     em
    35.25
     empirical
    34.75
     empowerment
    33.50
    Activations Density 0.057%

    No Known Activations