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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15955
    Prev
    Next
    INDEX
    Explanations

    say coating

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

    No Comments

    Negative Logits
     Schneider
    -21.25
     Throwable
    -16.25
     challenger
    -15.44
    婆婆
    -15.38
    女士
    -15.00
    .exc
    -14.94
     McConnell
    -14.81
     debugger
    -14.75
    _exceptions
    -14.25
    局局长
    -14.19
    POSITIVE LOGITS
     coating
    25.00
     cob
    22.38
     coated
    21.88
     Cob
    19.75
     coat
    19.50
     Cot
    19.50
    coat
    19.38
    镀
    19.00
     coatings
    19.00
     marin
    18.88
    Activations Density 0.560%

    No Known Activations