© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    say "register"

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

    No Comments

    Negative Logits
    信任
    -17.75
    _SIGNAL
    -17.75
    Signals
    -17.13
     Bond
    -16.50
     trusts
    -16.38
    的信任
    -16.25
    信号
    -16.00
    信
    -15.94
    行动
    -15.94
    操控
    -15.81
    POSITIVE LOGITS
     register
    18.75
    注册
    18.63
    -register
    18.13
    registers
    17.75
    REGISTER
    17.63
     regional
    17.50
    标准
    17.50
     региона
    17.25
    标准化
    17.13
    全县
    17.13
    Activations Density 0.181%

    No Known Activations