© 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. 15928
    Prev
    Next
    INDEX
    Explanations

    any => 培

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

    No Comments

    Negative Logits
    血腥
    -17.38
    陕
    -16.88
    $log
    -16.25
    장애
    -16.13
    -stream
    -16.13
     Anglo
    -15.88
    Scott
    -15.56
    江
    -15.38
    anghai
    -15.31
    Century
    -15.25
    POSITIVE LOGITS
     prism
    21.38
    焙
    19.63
     coffin
    19.13
    qr
    19.13
    铆
    19.00
    壶
    18.75
    暖气
    18.75
     Prism
    18.75
     solder
    18.25
     đá
    18.25
    Activations Density 0.522%

    No Known Activations