© 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. 15987
    Prev
    Next
    INDEX
    Explanations

    names

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

    No Comments

    Negative Logits
    楮
    -20.88
    擘
    -18.25
    龙门
    -17.50
     Roose
    -17.38
    旒
    -16.75
    纵横
    -16.75
    吞
    -16.75
    漷
    -16.63
    琏
    -16.63
     Ingram
    -16.63
    POSITIVE LOGITS
     chocolate
    20.88
    Chocolate
    19.25
     Sharon
    18.75
     Lauren
    18.38
     Kristen
    18.25
    圣诞
    18.25
     cocaine
    18.13
    地下室
    18.13
     Chocolate
    18.00
    寒假
    18.00
    Activations Density 0.990%

    No Known Activations