© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15101
    Prev
    Next
    INDEX
    Explanations

    Mediterranean diet

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

    No Comments

    Negative Logits
    entai
    -16.63
    icker
    -16.00
    ucas
    -15.75
    ween
    -15.56
    当前位置
    -15.38
    enity
    -15.00
    RequestId
    -15.00
    ệc
    -15.00
    losion
    -14.94
    ropical
    -14.94
    POSITIVE LOGITS
    odu
    13.31
     DESCRIPTION
    12.50
    觉
    12.38
    속
    12.31
    _Impl
    12.31
    δ
    12.19
     description
    12.13
    滩
    11.44
    念
    11.44
    σ
    11.38
    Activations Density 0.026%

    No Known Activations