© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    say "leg"

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

    No Comments

    Negative Logits
    interval
    -15.38
    eload
    -14.75
    FileSystem
    -14.56
    .idx
    -14.19
    abal
    -14.00
    .src
    -14.00
    amines
    -13.88
    modal
    -13.81
    [idx
    -13.75
    (idx
    -13.75
    POSITIVE LOGITS
     leg
    104.50
     Leg
    97.50
    Leg
    96.00
    leg
    89.00
    _leg
    87.50
    -leg
    83.50
     legs
    77.50
     LEG
    75.00
    腿
    74.50
    LEG
    72.00
    Activations Density 0.246%

    No Known Activations