© 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
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 730
    Prev
    Next
    INDEX
    Explanations

    say "Roman"

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

    No Comments

    Negative Logits
     Kotlin
    -25.88
     Greenville
    -25.25
     Eston
    -24.25
    在深圳
    -23.50
     kotlin
    -22.88
    倓
    -22.88
     QtCore
    -22.75
    (QtCore
    -22.63
     HK
    -22.63
    马来西亚
    -22.25
    POSITIVE LOGITS
    罗马
    51.25
     Roman
    47.25
     Rome
    45.25
    Roman
    43.00
     Romans
    42.75
     roman
    39.25
     Roma
    36.50
     ROM
    34.75
     Pompe
    33.75
    意大利
    32.25
    Activations Density 0.627%

    No Known Activations