© 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. 15995
    Prev
    Next
    INDEX
    Explanations

    playing cards

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

    No Comments

    Negative Logits
    写作
    -16.13
     ulcer
    -15.75
    atasets
    -15.75
    政府部门
    -15.25
    inox
    -15.13
    报告
    -15.06
    ibus
    -15.00
    _pol
    -14.94
    wpdb
    -14.88
    -pol
    -14.81
    POSITIVE LOGITS
     cards
    44.75
     card
    44.25
     Cards
    42.25
     Card
    40.50
    card
    39.75
    Card
    38.75
    (card
    38.75
    .cards
    38.25
    cards
    38.25
    -card
    37.75
    Activations Density 0.078%

    No Known Activations