© 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. 15814
    Prev
    Next
    INDEX
    Explanations

    say inflate

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

    No Comments

    Negative Logits
    岳阳
    -19.88
    情人节
    -19.75
    椰
    -19.13
    SQLite
    -18.88
    鹊
    -18.50
    三亚
    -18.38
     Egyptian
    -18.38
    菊
    -18.13
    端午
    -17.88
     moon
    -17.63
    POSITIVE LOGITS
    流转
    19.38
    透
    18.50
    膨胀
    18.25
    纾
    17.50
     Inflate
    17.50
    爆发
    17.50
    inflate
    17.38
    �
    17.38
    充
    17.25
    膨
    17.00
    Activations Density 0.739%

    No Known Activations