© 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. 3348
    Prev
    Next
    INDEX
    Explanations

    say object

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    面
    -19.25
    数
    -17.38
    形象
    -17.00
     item
    -16.38
     image
    -16.13
    面上
    -15.94
    ItemImage
    -15.75
     Item
    -15.75
    数量
    -15.69
    數
    -15.63
    POSITIVE LOGITS
    组织
    24.63
    object
    22.50
    組織
    22.00
     condition
    21.88
     object
    21.88
    _object
    21.75
     Condition
    21.13
    Object
    21.13
    _condition
    21.13
     Object
    20.88
    Activations Density 0.054%

    No Known Activations