© 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. 579
    Prev
    Next
    INDEX
    Explanations

    say Connecticut

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

    No Comments

    Negative Logits
    西宁
    -26.13
    PMC
    -24.25
     PMC
    -23.63
    湟
    -23.63
    青海
    -22.75
     PY
    -22.38
     Iranian
    -22.25
    青海省
    -22.13
     Iranians
    -20.00
    西安市
    -20.00
    POSITIVE LOGITS
     Connecticut
    53.50
     CT
    46.25
     Hartford
    45.00
    	ct
    42.25
    (ct
    42.25
     ct
    40.25
    CT
    37.75
    ct
    35.25
     Ct
    35.00
    _ct
    34.50
    Activations Density 0.066%

    No Known Activations