© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15649
    Prev
    Next
    INDEX
    Explanations

    say capitalized names

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

    No Comments

    Negative Logits
    雀
    -29.38
    小鸟
    -25.63
    smith
    -25.13
     bird
    -24.88
     Bird
    -24.38
    鸽
    -24.13
    鸟
    -24.00
     Mickey
    -23.00
    射击
    -23.00
    avian
    -22.88
    POSITIVE LOGITS
     Dustin
    21.63
     ASD
    20.00
    	buff
    19.63
    (buff
    19.38
     Christoph
    19.25
    栎
    19.25
     cyst
    19.00
     Krist
    18.75
    Laura
    18.63
     Sofia
    18.38
    Activations Density 5.158%

    No Known Activations