© 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. 3165
    Prev
    Next
    INDEX
    Explanations

    say "relationship"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    输入
    -23.38
     input
    -18.25
    .key
    -17.50
     输入
    -17.50
     key
    -17.38
    input
    -17.38
     element
    -17.38
     Key
    -17.38
    元素
    -17.25
    ,array
    -17.13
    POSITIVE LOGITS
    relationship
    22.13
     Relationship
    21.75
     relationship
    21.63
    _relationship
    21.25
    Relationship
    21.13
    -system
    21.00
     relationships
    20.75
    模型
    20.38
    部
    20.25
    モデル
    19.88
    Activations Density 0.192%

    No Known Activations