© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 506
    Prev
    Next
    INDEX
    Explanations

    say "ancient civilizations"

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

    No Comments

    Negative Logits
    碚
    -21.25
    赣州
    -20.63
     pineapple
    -20.13
    丹麦
    -19.63
     Puerto
    -19.38
    湛江
    -19.13
     Milwaukee
    -19.13
    滨海
    -18.88
     Manitoba
    -18.75
    MLS
    -18.63
    POSITIVE LOGITS
     Assy
    28.88
     Greek
    26.25
     Greeks
    24.75
    Greek
    24.75
    公元前
    24.63
    秦
    24.38
     Babylon
    24.13
     Greece
    24.00
     Egypt
    23.88
    秦国
    23.63
    Activations Density 0.503%

    No Known Activations