© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    say "gap"

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

    No Comments

    Negative Logits
    ycl
    -16.88
    scrollTop
    -16.63
    witch
    -16.38
    (curl
    -15.81
    集中
    -15.44
    	curl
    -15.38
     Lionel
    -15.38
    indle
    -15.25
    党总
    -15.13
     CURL
    -15.06
    POSITIVE LOGITS
     gap
    42.00
     gaps
    41.25
    空
    40.00
    gap
    40.00
     Gap
    35.75
    空白
    35.25
     fill
    35.00
    -gap
    34.75
    Gap
    34.50
    填补
    34.25
    Activations Density 0.290%

    No Known Activations