© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 522
    Prev
    Next
    INDEX
    Explanations

    say genome

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

    No Comments

    Negative Logits
     ventilation
    -21.88
    通风
    -20.25
     respir
    -18.00
    拘留
    -17.63
    Vent
    -17.63
     vent
    -17.63
    .ticket
    -17.50
    ODE
    -17.38
    篁
    -17.00
    Carbon
    -16.88
    POSITIVE LOGITS
     genome
    18.50
     genomic
    18.38
     flies
    17.75
    genome
    17.50
     locus
    17.25
    遗传
    17.13
     fly
    17.13
     DNA
    17.00
     genomes
    16.00
    基因
    15.81
    Activations Density 0.084%

    No Known Activations