© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16153
    Prev
    Next
    INDEX
    Explanations

    Coronal Mass

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

    No Comments

    Negative Logits
    绑
    -19.88
    浔
    -18.50
    电解
    -18.38
    艇
    -17.88
     enrichment
    -17.75
    矶
    -17.63
    enco
    -17.38
    oref
    -17.38
    匡
    -17.00
     cleansing
    -16.88
    POSITIVE LOGITS
    副院长
    19.50
    局副局长
    17.50
    副局长
    17.13
    Century
    16.88
    .Bl
    16.63
    logue
    16.63
    logan
    16.25
    Log
    16.25
    副总经理
    16.13
    楼梯
    16.00
    Activations Density 0.733%

    No Known Activations