© 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. 2043
    Prev
    Next
    INDEX
    Explanations

    动脉

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

    No Comments

    Negative Logits
     artery
    -23.00
     arteries
    -21.75
     ARCH
    -19.50
     Archer
    -19.50
     arrows
    -19.50
    -arrow
    -19.38
     Arch
    -19.38
    Arch
    -19.38
     Arlington
    -19.13
    Architecture
    -19.13
    POSITIVE LOGITS
    燃烧
    17.00
    aker
    15.25
    火
    14.94
    点燃
    14.75
    数据库
    14.75
     Biom
    13.94
    氢
    13.81
    祺
    13.81
    做饭
    13.75
    json
    13.44
    Activations Density 0.051%

    No Known Activations