© 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. 16258
    Prev
    Next
    INDEX
    Explanations

    核心素养

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

    No Comments

    Negative Logits
    fox
    -18.25
     bankruptcy
    -17.75
     deleted
    -17.63
    裤
    -17.63
     delet
    -17.50
    fax
    -17.13
     deletion
    -16.88
     deleting
    -16.88
     corrupt
    -16.75
     delete
    -16.63
    POSITIVE LOGITS
    策略
    17.63
    维度
    17.50
    _SCHEMA
    16.88
    ValueCollection
    16.63
     Strategies
    15.50
    发展目标
    15.00
    可视化
    14.69
    .cross
    14.63
     Resolver
    14.50
    alue
    14.44
    Activations Density 0.321%

    No Known Activations