© 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. 15474
    Prev
    Next
    INDEX
    Explanations

    say limits

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

    No Comments

    Negative Logits
    车内
    -16.00
    .sources
    -15.94
    /API
    -15.63
    车队
    -15.50
    车上
    -15.19
    queen
    -14.44
    ponse
    -14.31
    结构调整
    -14.25
    大气
    -14.19
    压力
    -13.88
    POSITIVE LOGITS
     limits
    19.00
     borders
    18.88
     lim
    18.75
     boundary
    18.00
    限
    17.75
    边界
    17.75
     boundaries
    17.63
    界限
    17.50
    imator
    17.25
    boundary
    17.13
    Activations Density 0.102%

    No Known Activations