© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15611
    Prev
    Next
    INDEX
    Explanations

    say animals

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

    No Comments

    Negative Logits
    setAttribute
    -17.25
    宫廷
    -16.75
    禀
    -16.25
    面子
    -15.94
    编辑
    -15.69
    ylie
    -15.63
     baskı
    -15.44
    命
    -15.38
    hurst
    -15.38
    uthor
    -15.31
    POSITIVE LOGITS
    动物
    32.25
     animal
    32.25
    鸟类
    31.88
     bird
    30.75
    鱼类
    30.50
     fish
    30.25
    fish
    29.50
     fishes
    29.13
     birds
    28.88
     animals
    28.63
    Activations Density 0.421%

    No Known Activations