© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    say "type"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     页面
    -15.56
     poil
    -15.31
    Spi
    -15.25
    页面
    -14.69
     Page
    -14.25
     страниц
    -14.00
    ман
    -13.94
    tó
    -13.56
    тро
    -13.50
    Page
    -13.19
    POSITIVE LOGITS
    型
    81.50
     type
    66.50
    ��
    64.00
    type
    59.00
     Type
    57.25
    类型
    56.75
    (type
    55.00
    Type
    54.00
    -type
    53.50
    	type
    52.50
    Activations Density 0.114%

    No Known Activations