© 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. 856
    Prev
    Next
    INDEX
    Explanations

    say Devanagari characters

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

    No Comments

    Negative Logits
    昆明
    -24.00
    泰国
    -21.00
     TCL
    -20.88
    石家庄
    -20.63
    TPL
    -20.50
     Jordan
    -20.00
    黑龙
    -20.00
    嵩
    -19.88
    长沙
    -19.88
     Riyadh
    -19.88
    POSITIVE LOGITS
    上海市
    36.75
    Italian
    36.50
     �
    36.50
     Italian
    36.50
     Italy
    36.25
     Italians
    35.50
     प
    34.50
     म
    34.00
     स
    33.50
     क
    33.25
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.