© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1188
    Prev
    Next
    INDEX
    Explanations

    Su‑prefixed city names

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

    No Comments

    Negative Logits
    江苏
    -20.88
    江南
    -20.75
    江苏省
    -18.88
    长三角
    -18.75
    江淮
    -17.88
    _gid
    -16.38
     chip
    -16.38
    蘇
    -16.25
    苏
    -16.13
    wind
    -16.00
    POSITIVE LOGITS
    编码
    18.50
    -ball
    17.50
    XML
    17.13
    枥
    17.00
    磁
    15.88
    leaning
    15.81
    unce
    15.31
    ball
    14.75
    Audio
    14.63
    洺
    14.56
    Activations Density 0.126%

    No Known Activations