© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16097
    Prev
    Next
    INDEX
    Explanations

    say cause

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

    No Comments

    Negative Logits
    Houston
    -19.63
    澡
    -17.50
    漱
    -17.38
     hü
    -17.13
    _quiz
    -17.13
     Houston
    -16.75
     WA
    -16.75
     Zub
    -16.63
     dq
    -16.13
     quizzes
    -16.13
    POSITIVE LOGITS
    导
    17.38
     cascade
    17.13
     Marker
    15.69
     marker
    15.50
     markers
    15.19
     mask
    15.13
     đạo
    14.69
    标志
    14.56
     porte
    14.38
    marker
    14.31
    Activations Density 0.327%

    No Known Activations