© 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. 2879
    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
    /dir
    -19.25
    	dir
    -16.38
     Ana
    -16.00
     conserv
    -15.94
     Conserv
    -15.25
     dir
    -15.25
     Dir
    -14.63
    註
    -14.63
    顾
    -14.56
    serv
    -14.38
    POSITIVE LOGITS
     leg
    23.13
    百
    22.25
     Leg
    20.75
    Leg
    20.50
     legs
    20.25
    方
    20.25
     pres
    19.88
    legs
    19.75
    _leg
    19.75
    -leg
    19.63
    Activations Density 0.173%

    No Known Activations