© 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. 11
    Prev
    Next
    INDEX
    Explanations

    say ID

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

    No Comments

    Negative Logits
    泸
    -20.13
    渝
    -19.50
    巴黎
    -18.63
    フランス
    -18.50
     CST
    -18.38
     french
    -18.13
    芙蓉
    -18.13
    Paris
    -18.00
     TEX
    -17.75
     Texans
    -17.63
    POSITIVE LOGITS
    (ID
    48.50
    <ID
    46.75
     ID
    46.00
    [ID
    43.75
    .ID
    43.00
    ,ID
    42.25
     IDC
    41.50
    ID
    41.50
    >ID
    40.75
    	ID
    40.25
    Activations Density 0.128%

    No Known Activations