© 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. 130
    Prev
    Next
    INDEX
    Explanations

    say "Malayalam letters"

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

    No Comments

    Negative Logits
    无锡
    -28.13
    兰州
    -26.00
    甘肃
    -26.00
    祁
    -25.75
    山西
    -25.63
    甘肃省
    -24.75
     Schwe
    -24.25
    陇
    -24.13
     Austria
    -23.88
    晋
    -23.88
    POSITIVE LOGITS
    �
    33.75
    ക
    32.00
    ത
    31.25
    ്�
    31.13
    റ
    30.13
    ൻ
    29.63
    �
    29.38
    ന
    29.25
    ല
    29.13
    പ
    28.50
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.