© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15990
    Prev
    Next
    INDEX
    Explanations

    say "end"

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

    No Comments

    Negative Logits
    tica
    -20.25
     Isis
    -16.88
    uty
    -16.50
     Orig
    -16.38
     mouths
    -15.88
    _lot
    -15.56
     кожи
    -15.38
    cosa
    -15.38
    akte
    -15.19
    ıkl
    -15.19
    POSITIVE LOGITS
    ender
    17.50
    缓
    16.50
    endors
    16.38
    建筑面积
    16.13
     endpoints
    16.00
    	end
    16.00
    ENDER
    15.81
    end
    15.69
    енд
    15.63
    uns
    15.25
    Activations Density 0.060%

    No Known Activations