© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    constant keyword

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    目录
    -23.50
    部门
    -19.13
     directory
    -17.75
     department
    -17.63
    -directory
    -16.75
    体系
    -15.81
    ETYPE
    -15.75
    团队
    -15.69
    department
    -15.25
     treatment
    -15.19
    POSITIVE LOGITS
     condition
    23.75
     component
    22.25
    constant
    21.63
    .constant
    21.38
     Condition
    21.25
    component
    21.00
    Condition
    21.00
     constant
    20.75
    Component
    20.63
     Component
    20.50
    Activations Density 0.059%

    No Known Activations