© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    say "cell"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    道
    -27.38
    範
    -17.63
     David
    -17.63
    范围
    -17.00
     approach
    -16.75
    大道
    -16.75
    目录
    -16.75
     framework
    -16.38
    David
    -16.38
     Approach
    -16.13
    POSITIVE LOGITS
     cell
    67.50
    细胞
    59.25
    cell
    59.25
     Cell
    57.75
    Cell
    55.75
    	cell
    55.25
    _cell
    53.50
    (cell
    51.50
    .cell
    51.00
    -cell
    50.75
    Activations Density 0.132%

    No Known Activations