© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    => 免疫

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

    No Comments

    Negative Logits
     immun
    -23.75
    免疫
    -23.25
     Immun
    -19.25
     innovate
    -18.00
     innovation
    -17.88
    消防
    -17.25
     innov
    -16.88
    imm
    -16.63
    火
    -16.63
    军工
    -16.50
    POSITIVE LOGITS
     EU
    18.38
     Sheep
    18.13
    欧洲
    17.88
    英超
    17.25
     European
    17.25
    Books
    16.50
    ESA
    16.38
     Browser
    16.38
     Eu
    16.13
     tree
    16.00
    Activations Density 0.058%

    No Known Activations