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

    Neuronpedia

    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. 456
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ft
    -21.63
    楚
    -21.38
     ct
    -21.00
    	ct
    -20.00
    洱
    -19.88
     cs
    -19.38
    .ct
    -19.25
    (ct
    -18.75
     Brittany
    -18.75
    阊
    -18.63
    POSITIVE LOGITS
     Koreans
    32.75
     Korean
    32.00
    吉林省
    31.25
     Korea
    30.50
     Pyongyang
    30.50
    朝鲜
    29.50
    是韩国
    28.88
    吉林
    28.75
    哈尔滨
    28.50
     Seoul
    28.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.