© 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. 1872
    Prev
    Next
    INDEX
    Explanations

    say "sports"

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

    No Comments

    Negative Logits
    树木
    -37.25
    木材
    -35.25
     Tree
    -34.75
     tree
    -33.75
    树
    -33.75
     trees
    -33.00
     TREE
    -31.50
     wood
    -30.75
    Trees
    -30.75
    -tree
    -30.50
    POSITIVE LOGITS
    口
    16.75
     athletic
    16.25
    sports
    16.13
     Phelps
    16.00
     athletes
    16.00
    体育
    15.81
     sports
    15.63
    石
    15.06
     sport
    14.31
    Sport
    14.00
    Activations Density 0.106%

    No Known Activations