© 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. 16037
    Prev
    Next
    INDEX
    Explanations

    say ratio

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

    No Comments

    Negative Logits
    聚
    -18.13
    山路
    -17.00
    Clusters
    -16.88
    cluster
    -16.88
     congreg
    -16.75
     anmeld
    -16.75
    enda
    -16.63
    厄
    -16.38
     clustered
    -16.25
    考证
    -16.25
    POSITIVE LOGITS
     ratio
    34.50
     ratios
    34.25
    ratio
    34.25
    Ratio
    31.00
     Ratio
    30.63
    比例
    30.00
    _ratio
    29.63
    的比例
    29.50
     Rat
    29.00
    _RATIO
    27.63
    Activations Density 0.100%

    No Known Activations