© 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. 15483
    Prev
    Next
    INDEX
    Explanations

    say bird

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

    No Comments

    Negative Logits
     Dustin
    -22.50
     cyst
    -20.38
    	buff
    -20.25
     Christoph
    -20.13
     ASD
    -20.00
     Sofia
    -20.00
    栎
    -19.88
    (buff
    -19.63
    Laura
    -19.50
     kf
    -19.25
    POSITIVE LOGITS
    雀
    27.75
    小鸟
    25.00
    smith
    24.63
     bird
    24.00
     Bird
    23.38
    鸟
    23.13
    鸽
    22.75
    射击
    22.25
    avian
    21.75
     Mickey
    21.63
    Activations Density 6.012%

    No Known Activations