© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14144
    Prev
    Next
    INDEX
    Explanations

    [Ring] => [Ring]

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

    No Comments

    Negative Logits
    模型
    -32.75
     model
    -28.00
     models
    -27.75
    モデル
    -24.88
    关系
    -24.88
    model
    -24.88
     Models
    -24.75
    MODEL
    -24.75
    输入
    -24.63
     модели
    -24.63
    POSITIVE LOGITS
    -buy
    16.50
     cover
    15.63
    IndexChanged
    15.31
    arbonate
    15.13
     buy
    15.06
    .getActivity
    14.94
    去买
    14.75
     buying
    14.63
    ASK
    14.44
    买
    14.44
    Activations Density 1.503%

    No Known Activations