© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    say 1

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     point
    -21.38
    point
    -21.00
     Point
    -20.63
    -point
    -20.25
    Point
    -19.88
    _point
    -19.75
    点
    -19.13
    	Point
    -18.88
    surface
    -18.75
    .point
    -18.50
    POSITIVE LOGITS
    位置
    19.50
     campo
    19.00
     field
    18.63
    阶段
    18.50
    条件
    17.88
     stage
    17.88
    Campo
    17.50
    选项
    17.50
     condition
    17.25
     Stage
    17.13
    Activations Density 0.260%

    No Known Activations