© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    Chinese historical texts

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

    No Comments

    Negative Logits
    汉
    -42.50
    漢
    -39.75
     Roman
    -24.75
    汉字
    -24.50
    汉族
    -24.38
     roman
    -24.25
     Han
    -23.25
    汉语
    -23.13
    HTML
    -22.00
    roman
    -21.88
    POSITIVE LOGITS
    �
    15.38
     Creative
    14.88
     creative
    14.88
    fires
    14.63
     creativity
    14.56
    吸毒
    14.56
    空调
    14.44
    urning
    14.25
    izon
    14.25
    Email
    14.25
    Activations Density 0.110%

    No Known Activations