© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 813
    Prev
    Next
    INDEX
    Explanations

    say "Apple"

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

    No Comments

    Negative Logits
    秦国
    -27.75
    聊城
    -24.13
    秦
    -24.00
    邯郸
    -23.88
    潼
    -23.13
     Mississippi
    -22.75
     Oklahoma
    -22.75
     Romania
    -22.50
    邢台
    -22.38
    德州
    -22.25
    POSITIVE LOGITS
     Apple
    56.50
    苹果
    56.00
    Apple
    52.75
    .apple
    50.25
     apple
    48.75
    apple
    45.25
     iOS
    44.75
    iOS
    44.00
    iPhone
    43.25
    -ios
    42.75
    Activations Density 0.295%

    No Known Activations