© 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. 624
    Prev
    Next
    INDEX
    Explanations

    say "Chinese cities"

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

    No Comments

    Negative Logits
    洮
    -21.75
     Uran
    -20.25
     Porno
    -18.50
    尿
    -17.75
     Loren
    -17.38
     Shade
    -17.13
     Bundes
    -17.00
    椴
    -17.00
     NM
    -16.88
     UC
    -16.63
    POSITIVE LOGITS
    武汉
    32.50
    武汉市
    29.50
     Wu
    27.00
    湖北
    26.88
     Hong
    24.88
    湖北省
    24.00
    珞
    23.75
    在深圳
    23.00
    Hong
    22.00
     Guang
    21.75
    Activations Density 0.085%

    No Known Activations