© 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. 87
    Prev
    Next
    INDEX
    Explanations

    say IN

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

    No Comments

    Negative Logits
    粤
    -21.75
    蘇
    -20.75
    苏
    -20.75
     Portuguese
    -20.50
     DL
    -20.25
    港澳
    -19.63
    Bay
    -19.50
    在香港
    -19.38
    (uuid
    -19.13
     europ
    -18.63
    POSITIVE LOGITS
     IN
    23.13
     Indiana
    22.88
    IN
    21.38
    	IN
    21.25
    -IN
    20.13
    Indiana
    19.88
     Indianapolis
    19.75
     �
    19.63
    .IN
    19.25
    (IN
    18.63
    Activations Density 0.546%

    No Known Activations