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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1596
    Prev
    Next
    INDEX
    Explanations

    say construction

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

    No Comments

    Negative Logits
    AI
    -33.00
     AI
    -32.25
     Pi
    -30.50
     pi
    -28.88
    (ai
    -28.63
     ai
    -28.50
    ai
    -28.25
    pi
    -28.13
     di
    -27.75
    Pi
    -27.63
    POSITIVE LOGITS
    构造
    21.00
     construction
    19.50
     Construct
    18.88
    Construction
    18.88
     constructions
    18.75
     constructing
    17.75
     Construction
    17.63
     construct
    17.38
    Construct
    16.50
     constructs
    16.50
    Activations Density 0.400%

    No Known Activations