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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16160
    Prev
    Next
    INDEX
    Explanations

    say "sh" words

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

    No Comments

    Negative Logits
    篦
    -20.25
     Grape
    -20.00
     mav
    -19.63
     grape
    -19.13
     Deborah
    -18.75
    xBF
    -18.38
    RAIN
    -18.13
    箅
    -18.00
     sqlite
    -17.75
    鸬
    -17.75
    POSITIVE LOGITS
    保险
    23.00
    保险公司
    19.88
    嘉
    19.38
    保險
    19.25
     Shields
    19.25
    (pad
    19.25
    (sh
    19.13
    	sh
    19.00
    sh
    18.88
     pad
    18.38
    Activations Density 4.363%

    No Known Activations