© 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. 855
    Prev
    Next
    INDEX
    Explanations

    say "Telugu letters"

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

    No Comments

    Negative Logits
    浦东
    -29.63
    上海
    -28.88
    上海市
    -27.50
    在上海
    -26.75
     Naples
    -26.25
     Luigi
    -24.75
     Venice
    -24.38
     Laguna
    -24.00
     Luca
    -23.13
    沪
    -23.13
    POSITIVE LOGITS
    �
    35.75
     �
    35.75
    �
    35.50
    న
    34.75
    డ
    34.50
    గ
    33.00
    ర
    33.00
    ద
    32.50
    ల
    32.25
    క
    32.00
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.