© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    say "panel"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (pa
    -22.50
    pii
    -20.38
    (pm
    -20.38
    (pb
    -19.50
     Palmer
    -19.13
    (pf
    -18.88
    pb
    -18.13
     unp
    -17.38
     pm
    -17.00
     pencils
    -16.88
    POSITIVE LOGITS
     panel
    60.75
     Panel
    58.75
    Panel
    54.25
    panel
    54.00
    .panel
    50.00
    _panel
    47.25
    	panel
    46.75
    -panel
    46.50
     panels
    44.75
     Panels
    43.00
    Activations Density 0.022%

    No Known Activations