© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3135
    Prev
    Next
    INDEX
    Explanations

    say "collection"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    式
    -18.50
    式的
    -17.50
    ��
    -17.38
    EventType
    -15.75
    按钮
    -15.69
    EndPoint
    -15.50
    模式
    -15.19
     EventType
    -15.06
     eventType
    -14.81
    _EVENT
    -14.75
    POSITIVE LOGITS
     collection
    71.00
    collection
    66.00
     Collection
    64.00
    Collection
    63.00
    _collection
    59.00
    	Collection
    54.25
    -collection
    53.75
    (collection
    52.75
    .collection
    52.50
     collections
    51.50
    Activations Density 0.152%

    No Known Activations