© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 229
    Prev
    Next
    INDEX
    Explanations

    同步更新

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

    No Comments

    Negative Logits
     EI
    -16.13
    下车
    -15.69
     Petr
    -15.13
    钓
    -14.94
    .tracks
    -14.94
    _tracks
    -14.88
    .Track
    -14.63
     fj
    -14.63
    通车
    -14.50
    ‐
    -14.13
    POSITIVE LOGITS
    歲
    21.13
       
    18.75
      
    18.13
    銷售
    17.50
    報告
    16.75
    殘
    16.63
    ?option
    16.38
     ↵
    16.25
     
    16.00
     hoàn
    16.00
    Activations Density 0.805%

    No Known Activations