© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    [教] => [教唆]

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

    No Comments

    Negative Logits
    教
    -38.50
    教会
    -29.00
     teaching
    -26.75
     Teach
    -25.50
     teach
    -24.25
     Teaching
    -23.50
    教学
    -22.13
    Te
    -21.25
     teaches
    -21.00
    教育教学
    -20.75
    POSITIVE LOGITS
     Sym
    16.88
     Harley
    16.88
    Sym
    16.88
    золот
    16.13
    数字
    16.13
    亿美元
    16.13
    sym
    16.00
     mountain
    16.00
    黄金
    15.88
    cka
    15.63
    Activations Density 0.080%

    No Known Activations