© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15994
    Prev
    Next
    INDEX
    Explanations

    say "posters"

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

    No Comments

    Negative Logits
    abox
    -16.75
     nug
    -16.63
    =ax
    -16.25
    Processor
    -15.94
    ær
    -15.94
    _recipe
    -15.63
     axe
    -15.50
    靴
    -15.38
    rut
    -15.38
    编织
    -15.25
    POSITIVE LOGITS
     poster
    25.25
     posters
    25.00
    海报
    24.50
    poster
    24.13
    张贴
    23.00
     posts
    22.75
    張貼
    22.50
     posting
    22.25
    标语
    21.75
    挂
    21.50
    Activations Density 0.295%

    No Known Activations