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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    viral genotypes

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

    No Comments

    Negative Logits
    (Channel
    -18.50
    /videos
    -17.63
    演讲
    -17.38
     Channels
    -17.25
     CHANNEL
    -17.13
    CHANNEL
    -16.38
    .learn
    -16.25
    channels
    -16.13
    learning
    -16.13
     learning
    -16.00
    POSITIVE LOGITS
    基因
    19.00
     circulated
    18.88
     circulating
    18.88
     circulation
    18.38
     isol
    18.13
     gen
    18.13
     Gen
    17.75
     genomes
    17.63
     genes
    17.63
    Gen
    17.63
    Activations Density 0.215%

    No Known Activations