© 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. 1122
    Prev
    Next
    INDEX
    Explanations

    [唐] => [唐]

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

    No Comments

    Negative Logits
    大唐
    -31.25
    唐朝
    -30.13
    唐代
    -24.25
    唐
    -21.50
    Trees
    -20.88
    李白
    -20.50
     Trees
    -20.25
     TREE
    -20.25
    trees
    -19.38
     Tolkien
    -19.00
    POSITIVE LOGITS
    蛋白
    16.50
     nutritional
    15.50
    cape
    15.50
    营养
    15.00
    /music
    15.00
    心理
    15.00
    ches
    14.81
    che
    14.69
    茸
    14.13
    欣赏
    14.00
    Activations Density 0.105%

    No Known Activations