© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14821
    Prev
    Next
    INDEX
    Explanations

    say war

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

    No Comments

    Negative Logits
    QUEST
    -19.00
    INSTALL
    -16.88
    legg
    -16.63
    赏析
    -16.38
    cobra
    -15.63
    Sab
    -15.50
    installation
    -15.50
    .Component
    -15.44
    �
    -15.38
     installs
    -15.38
    POSITIVE LOGITS
     wars
    21.63
    战争
    21.63
     World
    21.50
     war
    21.50
    war
    20.88
     WWII
    20.63
    War
    20.38
    World
    19.38
     War
    19.00
     world
    18.88
    Activations Density 0.060%

    No Known Activations