© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15953
    Prev
    Next
    INDEX
    Explanations

    network terminology

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

    No Comments

    Negative Logits
     turbo
    -22.38
     centrif
    -22.00
     Bulld
    -21.38
    胭
    -20.88
     helicopt
    -20.88
     vib
    -20.75
    傈
    -20.25
     Pumpkin
    -20.13
     pumpkin
    -20.00
     Guill
    -20.00
    POSITIVE LOGITS
     WHATSOEVER
    14.88
    有条件的
    14.69
    actical
    13.25
     Shows
    13.00
    部份
    12.81
    相识
    12.63
    =YES
    12.56
    よね
    12.50
    iente
    12.44
     Networks
    12.44
    Activations Density 2.197%

    No Known Activations