© 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. 217
    Prev
    Next
    INDEX
    Explanations

    say "genetic"

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

    No Comments

    Negative Logits
    杯
    -20.25
    客栈
    -20.25
    佤
    -17.63
     Boxing
    -16.75
    营
    -16.63
     vase
    -16.63
    =torch
    -16.63
    villa
    -16.50
    torch
    -16.50
     cups
    -16.50
    POSITIVE LOGITS
    基因
    37.00
     gene
    32.25
    转基因
    31.75
     genes
    31.63
     GMO
    29.75
     Gene
    28.63
    gene
    28.63
    genes
    28.50
    生物
    28.50
     genetic
    28.00
    Activations Density 0.131%

    No Known Activations