© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    say reading

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

    No Comments

    Negative Logits
    Portland
    -17.63
    opo
    -16.50
     Savannah
    -16.13
    东海
    -15.88
     vag
    -15.75
     Somerset
    -15.56
    ocha
    -15.44
    porte
    -15.44
    chap
    -15.44
     renegot
    -15.25
    POSITIVE LOGITS
    读
    20.13
    讀
    19.75
     mark
    19.63
    旋
    19.38
    reading
    18.75
     Reading
    18.75
     reading
    18.63
    标
    18.50
    滑
    18.50
     read
    18.13
    Activations Density 0.085%

    No Known Activations