© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15695
    Prev
    Next
    INDEX
    Explanations

    say activity

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

    No Comments

    Negative Logits
     backyard
    -18.25
    虾
    -18.00
    Seeder
    -17.50
    小龙虾
    -17.25
     Ramadan
    -17.13
     scooter
    -17.00
     seeds
    -16.75
     rusty
    -16.63
     seed
    -16.38
    <tag
    -16.38
    POSITIVE LOGITS
    活动
    26.75
     activities
    24.50
    activities
    23.13
     Activities
    23.00
    Activities
    22.25
    活动中
    22.25
    经营活动
    21.75
     activity
    21.63
     Activity
    21.25
    _activities
    20.63
    Activations Density 0.536%

    No Known Activations