© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 588
    Prev
    Next
    INDEX
    Explanations

    say "AT" words

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

    No Comments

    Negative Logits
    晋江
    -20.50
    浔
    -19.38
    Portland
    -18.00
    opus
    -17.75
    赣
    -17.50
    福建
    -17.38
    江西
    -16.63
    /fw
    -16.50
    _fb
    -16.50
    济宁
    -16.38
    POSITIVE LOGITS
     AT
    68.50
    (AT
    66.50
    AT
    66.50
    	AT
    55.00
     ATS
    43.75
    ATS
    42.75
    _AT
    42.00
     ATM
    41.75
     ATL
    40.50
     ATP
    38.00
    Activations Density 0.352%

    No Known Activations