© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    say "contains l"

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

    No Comments

    Negative Logits
    裼
    -16.25
    袆
    -15.56
     Burgess
    -15.56
    芗
    -14.69
    キュ
    -14.63
     Kirby
    -14.06
    三年级
    -14.00
    ạy
    -13.94
    包围
    -13.94
     FOX
    -13.94
    POSITIVE LOGITS
    (dl
    33.75
     DL
    33.75
    xl
    32.75
    อล
    32.50
    dl
    32.50
    SL
    32.25
    OL
    32.25
    oll
    31.88
    DL
    31.88
    rl
    31.75
    Activations Density 7.047%

    No Known Activations