© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    say dairy

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

    No Comments

    Negative Logits
     Wildcats
    -18.38
    翟
    -18.25
    Arizona
    -17.75
    炼
    -17.63
     CGI
    -17.38
    cgi
    -17.13
    长春
    -17.13
    猕
    -17.00
     суд
    -16.88
    سيد
    -16.88
    POSITIVE LOGITS
     Cream
    20.63
    奶
    20.00
     milk
    19.88
     cream
    19.25
     Milk
    18.88
     soap
    18.88
     Soap
    18.88
    酥
    18.75
    乳
    18.50
     dak
    18.25
    Activations Density 1.001%

    No Known Activations