© 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. 15869
    Prev
    Next
    INDEX
    Explanations

    say advancement

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

    No Comments

    Negative Logits
    Function
    -17.38
    -function
    -16.38
     Function
    -16.38
    技术
    -16.25
     FUNCTION
    -16.25
    函数
    -16.25
     function
    -16.13
    .fm
    -15.75
     technology
    -15.56
     tekn
    -15.25
    POSITIVE LOGITS
     advance
    18.13
     Advance
    17.50
     progress
    17.13
     advances
    17.00
     stack
    16.88
     stacks
    16.88
    advance
    16.63
    先进
    16.13
    baugh
    16.13
    _stack
    16.13
    Activations Density 0.191%

    No Known Activations