© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14194
    Prev
    Next
    INDEX
    Explanations

    say "ships"

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

    No Comments

    Negative Logits
    WRAPPER
    -17.13
     Gül
    -16.75
    制品
    -16.50
    _kel
    -16.50
    ện
    -16.50
    Xã
    -16.38
     ООО
    -16.38
    llib
    -16.38
     tavern
    -15.94
    农副产品
    -15.94
    POSITIVE LOGITS
    舰队
    19.63
    水面
    19.13
    艦
    18.63
    舰
    16.50
    鱼
    16.25
     torpedo
    16.13
    航母
    16.00
    艘
    16.00
     submar
    15.94
     naval
    15.88
    Activations Density 0.354%

    No Known Activations