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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16363
    Prev
    Next
    INDEX
    Explanations

    say "type" words

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

    No Comments

    Negative Logits
     imperial
    -16.75
    王朝
    -16.13
     queens
    -16.13
    净值
    -15.56
    quared
    -15.50
    皇后
    -15.25
    пат
    -15.25
    皇帝
    -15.25
     queen
    -14.81
     Owens
    -14.81
    POSITIVE LOGITS
    类型
    58.50
     type
    56.25
     Type
    52.75
    type
    52.75
     types
    52.00
    Type
    50.25
    types
    48.25
    类型的
    47.75
     Types
    47.75
    _type
    47.75
    Activations Density 0.347%

    No Known Activations