© 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. 662
    Prev
    Next
    INDEX
    Explanations

    say US states

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

    No Comments

    Negative Logits
    杭州市
    -22.38
     Helsinki
    -22.25
    成都
    -22.00
    合肥市
    -21.50
    成都市
    -21.25
    济南市
    -21.25
    九江
    -21.13
     Melbourne
    -20.75
     Toronto
    -20.75
     Finnish
    -20.63
    POSITIVE LOGITS
    GW
    17.63
     Pv
    16.88
    萨
    16.25
    GA
    15.94
     CSP
    15.75
    Msp
    15.69
    队员
    15.56
    SA
    15.31
     PA
    15.25
    薩
    15.13
    Activations Density 0.209%

    No Known Activations