© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 22
    Prev
    Next
    INDEX
    Explanations

    say "Kh"

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

    No Comments

    Negative Logits
     MSR
    -17.50
     NT
    -16.75
    果汁
    -16.13
    福州
    -15.75
    Boston
    -15.56
    东京
    -15.38
    香菇
    -15.25
    (PC
    -15.13
    wine
    -15.00
     Portugal
    -14.88
    POSITIVE LOGITS
     Kh
    70.00
    Kh
    67.00
     KH
    58.75
    kh
    55.25
     kh
    54.50
    KH
    53.00
     Khal
    34.75
    akh
    33.25
     Khan
    31.13
     Kb
    30.38
    Activations Density 0.060%

    No Known Activations