© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1797
    Prev
    Next
    INDEX
    Explanations

    直流

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    禾
    -20.50
    涑
    -17.63
    Float
    -17.38
     Potter
    -16.75
    党员
    -16.50
    JavaScript
    -16.38
    flamm
    -16.25
    政治
    -16.25
     JavaScript
    -16.13
    舫
    -16.13
    POSITIVE LOGITS
     energetic
    19.00
     video
    17.75
     Steele
    17.25
    vide
    16.88
     ENERGY
    16.75
    ATO
    16.50
    eker
    16.38
    video
    16.38
     StyleSheet
    16.25
     Nets
    16.13
    Activations Density 0.220%

    No Known Activations