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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 171
    Prev
    Next
    INDEX
    Explanations

    => 潮

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

    No Comments

    Negative Logits
     Gem
    -21.00
    诸葛
    -20.75
    璠
    -20.13
    ót
    -19.88
     López
    -19.50
     maç
    -19.38
    玉石
    -18.88
    菝
    -18.88
    伐
    -18.63
     Jesús
    -18.63
    POSITIVE LOGITS
    潮
    45.25
    汕头
    40.50
    汕
    27.00
    濠
    25.63
     Indonesian
    23.13
    濉
    23.00
     Adelaide
    22.63
    朔
    21.75
    澄
    20.75
    汫
    20.63
    Activations Density 0.025%

    No Known Activations