© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3061
    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
    antic
    -16.88
     Rev
    -16.50
    _ant
    -15.81
    anten
    -15.81
     ANT
    -15.75
    Rev
    -15.63
     antis
    -15.38
     Ant
    -15.31
    antity
    -15.25
     Mat
    -14.94
    POSITIVE LOGITS
     et
    70.50
    (et
    64.50
    _et
    58.25
    .et
    58.00
    et
    55.75
    Et
    55.75
    -et
    55.50
     Et
    55.25
     ET
    51.00
    ET
    46.25
    Activations Density 0.098%

    No Known Activations