© 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. 15969
    Prev
    Next
    INDEX
    Explanations

    Hebrew letters

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

    No Comments

    Negative Logits
    保险
    -23.50
    保险公司
    -20.38
    	sh
    -20.25
     Shields
    -20.13
    (sh
    -20.00
    保險
    -20.00
    嘉
    -19.88
    (pad
    -19.63
    sh
    -19.38
     pad
    -18.75
    POSITIVE LOGITS
    篦
    19.50
     Grape
    18.63
     mav
    18.50
     grape
    18.13
     Deborah
    17.75
    xBF
    17.63
    箅
    17.63
    RAIN
    17.13
    鸬
    17.00
     rdf
    16.63
    Activations Density 4.238%

    No Known Activations