© 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. 674
    Prev
    Next
    INDEX
    Explanations

    say "梅"

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

    No Comments

    Negative Logits
    STA
    -21.75
     STA
    -21.75
    BAT
    -19.88
    IDA
    -18.63
    UA
    -18.25
     BA
    -18.13
    咸阳
    -17.88
     GW
    -17.75
     WA
    -17.75
    _FA
    -17.75
    POSITIVE LOGITS
    梅
    63.25
     CM
    50.25
    CM
    47.25
    (cm
    44.25
     cm
    41.75
    	cm
    41.50
    梅花
    41.00
    _cm
    40.75
    cm
    40.25
     ML
    39.75
    Activations Density 0.071%

    No Known Activations