© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15414
    Prev
    Next
    INDEX
    Explanations

    say "asthma"

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

    No Comments

    Negative Logits
     kino
    -19.63
    太阳能
    -18.38
     ser
    -17.88
     Salad
    -17.75
     cade
    -17.50
    (song
    -16.25
    歌词
    -16.25
    甑
    -16.13
    _tran
    -16.00
    transpose
    -15.94
    POSITIVE LOGITS
     asthma
    24.63
     breath
    24.63
     Ast
    24.38
     bron
    23.00
    ast
    22.50
    哮喘
    22.38
     Breath
    21.63
     ast
    21.50
     breathe
    21.25
    (ast
    20.75
    Activations Density 0.088%

    No Known Activations