© 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. 3321
    Prev
    Next
    INDEX
    Explanations

    say "container"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    日
    -22.88
    Phase
    -21.00
     phase
    -20.88
     Phase
    -20.25
    field
    -20.25
    phase
    -20.00
     field
    -19.38
    _phase
    -18.75
    Field
    -18.38
     day
    -18.38
    POSITIVE LOGITS
     container
    58.75
    容器
    51.50
    container
    51.50
     Container
    49.00
    Container
    48.25
    	container
    48.00
    _container
    47.00
    .container
    47.00
    (container
    43.75
    -container
    43.25
    Activations Density 0.080%

    No Known Activations