© 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. 785
    Prev
    Next
    INDEX
    Explanations

    say "moon" words

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

    No Comments

    Negative Logits
     Svens
    -25.75
    沂
    -24.38
     Fargo
    -24.25
    潍坊
    -24.13
     Stockholm
    -23.75
     NJ
    -23.50
    淄博
    -23.50
     Swedish
    -22.38
    东营
    -22.25
    gaard
    -22.13
    POSITIVE LOGITS
     lunar
    33.00
     Lunar
    30.38
     Moon
    28.25
     moon
    26.88
    蟾
    26.75
    Moon
    25.63
    moon
    23.50
    月亮
    23.38
    嫦
    22.75
    楚
    22.63
    Activations Density 0.120%

    No Known Activations