© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 716
    Prev
    Next
    INDEX
    Explanations

    say Song dynasty

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

    No Comments

    Negative Logits
    伊拉
    -19.75
    hashCode
    -19.25
     hashCode
    -18.25
    鳕
    -18.00
    斯塔
    -17.38
    髂
    -16.88
    砾
    -16.75
     Jama
    -16.75
    getResponse
    -16.50
    番茄
    -16.25
    POSITIVE LOGITS
    宋
    47.00
    北宋
    45.75
    宋代
    43.50
    南宋
    42.50
    汴
    36.00
    PY
    31.88
     PY
    31.50
     Zhang
    30.50
     Python
    29.75
     Py
    29.25
    Activations Density 0.274%

    No Known Activations