© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    say "frame"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     department
    -22.00
    _department
    -20.00
     Department
    -19.88
    各部门
    -19.50
    Department
    -19.38
    department
    -19.13
     path
    -19.00
    path
    -18.63
    条件
    -18.63
     departments
    -18.50
    POSITIVE LOGITS
    Frame
    20.13
     Frame
    20.00
     frame
    19.63
    -framework
    19.50
    frame
    19.50
    FRAME
    19.25
    _FRAME
    18.25
    _frame
    18.13
    框架
    18.00
     frames
    17.75
    Activations Density 0.647%

    No Known Activations