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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 316
    Prev
    Next
    INDEX
    Explanations

    say Kannada letters

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

    No Comments

    Negative Logits
    亳
    -26.88
    合肥
    -24.13
    合肥市
    -23.00
    庐
    -21.88
    (cx
    -20.50
     Warsaw
    -20.38
    安徽
    -20.25
     cx
    -19.75
    蚌埠
    -19.63
     CX
    -19.50
    POSITIVE LOGITS
    ರ
    33.00
    广西
    30.88
     �
    30.38
    �
    30.00
    ಕ
    29.38
    �
    29.38
    ಡ
    29.38
    ಅ
    29.13
    ಸ
    28.88
     LSU
    28.75
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.