© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15449
    Prev
    Next
    INDEX
    Explanations

    say hierarchy

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

    No Comments

    Negative Logits
    蝇
    -18.63
     camp
    -18.13
     camps
    -18.00
    恐慌
    -17.75
    ynchronization
    -17.63
    坚果
    -16.50
     plywood
    -16.38
    _sync
    -16.25
     Candy
    -16.13
    ThreadPool
    -16.13
    POSITIVE LOGITS
    等级
    28.63
    尊严
    25.38
    Hier
    22.75
    级
    22.63
     Hier
    21.88
    尊
    21.88
    Hierarchy
    21.00
     hier
    20.88
     feudal
    20.88
     hierarchy
    20.50
    Activations Density 0.359%

    No Known Activations