© 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. 997
    Prev
    Next
    INDEX
    Explanations

    say ancient Chinese states

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

    No Comments

    Negative Logits
    GA
    -20.50
    빵
    -20.25
     GA
    -19.63
     Bakery
    -19.63
    白糖
    -18.75
    _AST
    -18.63
    cake
    -18.25
    蔗
    -17.75
    _ast
    -17.75
     Delhi
    -17.75
    POSITIVE LOGITS
    濮
    21.13
    薳
    18.50
    郤
    17.88
    莒
    17.38
    𫇭
    17.25
    僖
    17.13
    大夫
    17.00
     Pg
    16.63
    pg
    16.38
     pg
    16.00
    Activations Density 0.101%

    No Known Activations