© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    say "oxidation" words

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

    No Comments

    Negative Logits
     doll
    -20.00
     babies
    -19.88
     baby
    -18.13
     rocked
    -17.88
     caul
    -17.63
    毯
    -17.50
     Babies
    -17.00
    嬰
    -16.88
     diapers
    -16.88
     infant
    -16.75
    POSITIVE LOGITS
     oxid
    34.00
     antioxidant
    32.00
    氧化
    31.88
     antioxid
    31.13
     oxidation
    30.00
     Ox
    28.75
    oxid
    28.50
    抗氧化
    28.38
     oxidative
    28.38
     antioxidants
    25.50
    Activations Density 0.108%

    No Known Activations