© 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. 15471
    Prev
    Next
    INDEX
    Explanations

    say "electric"

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

    No Comments

    Negative Logits
     crank
    -17.38
    贬值
    -17.25
    亭
    -17.13
     Hemisphere
    -16.88
    直升机
    -16.75
    缙
    -16.13
    缸
    -15.31
    kur
    -15.25
    曲
    -15.06
    кур
    -15.06
    POSITIVE LOGITS
    电
    22.00
     electric
    20.63
     elect
    20.50
     Elect
    20.00
    electric
    19.38
    elect
    19.00
    Elect
    19.00
    用电
    18.63
     ele
    18.25
     ELECT
    18.00
    Activations Density 0.036%

    No Known Activations