© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14374
    Prev
    Next
    INDEX
    Explanations

    do not say dairy

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

    No Comments

    Negative Logits
    奶
    -21.75
     Cream
    -21.63
     milk
    -21.00
     Milk
    -20.25
     cream
    -20.25
     Soap
    -19.75
     Dairy
    -19.50
     soap
    -19.38
    乳
    -19.13
     sữa
    -18.75
    POSITIVE LOGITS
    翟
    18.13
    cgi
    17.75
    Arizona
    17.50
     Wildcats
    17.38
    炼
    17.00
     CGI
    16.88
    长春
    16.50
    سيد
    16.50
     Arizona
    16.38
    眩
    16.38
    Activations Density 0.979%

    No Known Activations