© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 911
    Prev
    Next
    INDEX
    Explanations

    say "zoo"

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

    No Comments

    Negative Logits
    烟草
    -20.25
     farmer
    -17.88
     peasant
    -17.63
    抽烟
    -17.25
     Tobacco
    -17.00
    .weapon
    -16.88
     tobacco
    -16.88
    Weapons
    -16.75
     volley
    -16.63
     weapon
    -16.50
    POSITIVE LOGITS
    动物园
    27.88
     zoo
    26.50
     Zoo
    26.13
     Aquarium
    22.75
    园
    22.50
    園
    22.38
    场馆
    21.75
     aquarium
    21.63
    漓
    19.38
     parks
    19.25
    Activations Density 0.098%

    No Known Activations