© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    say meteor

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

    No Comments

    Negative Logits
    rev
    -16.25
     Qual
    -15.94
     qual
    -15.94
    elib
    -15.63
    .fac
    -15.06
    质
    -15.06
    Qual
    -14.88
    _qual
    -14.75
     Aug
    -14.63
     em
    -14.50
    POSITIVE LOGITS
     meteor
    59.50
     Meteor
    52.50
    Meteor
    51.75
    meteor
    49.25
    气象
    41.75
     Met
    36.75
     MET
    36.50
     weather
    35.75
    元
    35.25
     Weather
    35.00
    Activations Density 0.045%

    No Known Activations