© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14344
    Prev
    Next
    INDEX
    Explanations

    say religious building

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

    No Comments

    Negative Logits
    写作
    -19.00
    READING
    -16.88
     Writing
    -16.88
    .Write
    -16.75
     writing
    -16.38
     YELLOW
    -16.13
    -writing
    -16.13
    朗诵
    -16.00
    成员国
    -16.00
    Writing
    -15.81
    POSITIVE LOGITS
    教堂
    18.38
     basil
    17.25
     Cathedral
    16.38
     churches
    15.38
     Basil
    14.94
    々
    14.19
    Minor
    13.75
    严肃
    13.56
     neglig
    13.44
    [method
    13.13
    Activations Density 0.033%

    No Known Activations