© 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. 16226
    Prev
    Next
    INDEX
    Explanations

    author names

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

    No Comments

    Negative Logits
     StringComparison
    -18.75
    伞
    -16.88
     forks
    -16.75
    夏
    -16.50
     compareTo
    -16.38
     Fork
    -16.13
    砧
    -16.00
     pouring
    -15.94
    fork
    -15.94
    artial
    -15.88
    POSITIVE LOGITS
    logan
    19.50
    cona
    18.38
     Shay
    17.88
    -con
    17.63
    isy
    17.63
    (con
    17.25
     Conway
    17.00
     Daytona
    16.88
     Snyder
    16.75
    con
    16.25
    Activations Density 0.498%

    No Known Activations