© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16349
    Prev
    Next
    INDEX
    Explanations

    say "acronyms"

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

    No Comments

    Negative Logits
    LEEP
    -18.75
     Colin
    -17.00
     crawled
    -16.63
     crawling
    -16.63
    Scotland
    -16.50
    	im
    -16.13
     Jungle
    -16.13
     colony
    -16.13
     sleeping
    -15.88
     col
    -15.75
    POSITIVE LOGITS
     messageId
    17.88
    CAR
    17.25
    中美
    17.25
     HDMI
    17.25
     CAR
    17.00
     AHL
    16.88
     Carb
    16.50
     refr
    16.13
     AQ
    16.00
    .car
    15.88
    Activations Density 0.883%

    No Known Activations