© 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. 985
    Prev
    Next
    INDEX
    Explanations

    say "lua"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    悯
    -19.38
     Hampton
    -19.25
     Hamm
    -19.00
    ⁃
    -18.13
    老太太
    -17.50
    ioned
    -17.50
     enjo
    -17.50
    illard
    -17.38
    _hd
    -17.38
    uld
    -17.38
    POSITIVE LOGITS
    .lua
    35.50
    lua
    33.50
     lua
    33.50
     Lua
    31.75
    Lua
    28.25
    	lua
    26.13
     --
    25.63
    _lua
    25.50
    (lua
    25.13
     tonumber
    25.00
    Activations Density 0.052%

    No Known Activations