© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 467
    Prev
    Next
    INDEX
    Explanations

    say coffee

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

    No Comments

    Negative Logits
     LZ
    -21.63
    沔
    -19.88
    郾
    -18.13
    螈
    -17.13
    南阳
    -17.13
     fz
    -17.00
     herpes
    -17.00
     Walton
    -16.88
    手术
    -16.88
     Yue
    -16.75
    POSITIVE LOGITS
     coffee
    63.75
    咖啡
    63.25
     Coffee
    57.50
    コーヒー
    56.25
    Coffee
    54.00
    coffee
    53.00
     caffeine
    49.25
     espresso
    43.50
    茶
    43.00
    コーヒ
    42.25
    Activations Density 0.128%

    No Known Activations