© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15936
    Prev
    Next
    INDEX
    Explanations

    central

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

    No Comments

    Negative Logits
    angelo
    -17.88
    shaw
    -17.75
    anto
    -16.63
    ement
    -15.75
     Shaw
    -15.31
    娼
    -15.31
    iete
    -14.94
     Shawn
    -14.88
     TRAN
    -14.75
    -op
    -14.69
    POSITIVE LOGITS
    dcc
    15.50
    计算机
    15.31
    computer
    15.19
    柚
    15.19
     computer
    15.00
    Computer
    14.75
    comput
    14.69
    Comput
    14.31
     computers
    14.25
     dispersed
    14.00
    Activations Density 0.076%

    No Known Activations