© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    say discourse markers

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

    No Comments

    Negative Logits
     encode
    -16.25
     Spiel
    -16.13
     kode
    -15.81
     lệ
    -15.50
    陟
    -15.25
    ctal
    -15.19
     Ere
    -15.13
    catalog
    -14.88
    绣
    -14.81
     Encode
    -14.69
    POSITIVE LOGITS
    的房子
    20.75
    的话
    20.50
    比如说
    19.38
    你怎么
    19.00
    过程当中
    18.50
    这个时候
    18.38
    什么东西
    18.25
    你说
    17.88
     talking
    17.63
    这些东西
    17.50
    Activations Density 1.217%

    No Known Activations