© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    say "frame"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    部
    -23.25
     group
    -22.00
     property
    -21.63
    event
    -21.38
     event
    -21.38
    group
    -21.13
     condition
    -20.88
     Group
    -20.75
    method
    -20.50
    群
    -20.50
    POSITIVE LOGITS
     frame
    36.75
    frame
    31.75
    Frame
    30.38
    _frame
    30.13
    	frame
    29.00
     Frame
    29.00
    (frame
    28.13
    .frame
    28.00
    帧
    27.88
    框架
    26.50
    Activations Density 0.176%

    No Known Activations