© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    say "copy"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    领域
    -22.88
    领域的
    -20.63
    領域
    -20.25
    (field
    -19.25
     field
    -18.13
    (domain
    -17.88
    (parameter
    -17.88
     domain
    -17.88
    field
    -17.63
     phase
    -17.63
    POSITIVE LOGITS
    公司
    35.50
     company
    34.25
    company
    31.75
    公司在
    31.75
    公司的
    31.50
    公司将
    30.13
    Company
    29.88
     Company
    29.38
     copy
    29.00
    (company
    28.63
    Activations Density 0.040%

    No Known Activations