© 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. 15839
    Prev
    Next
    INDEX
    Explanations

    [post] => [post]

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

    No Comments

    Negative Logits
    二线
    -18.88
    pagesize
    -16.13
     input
    -16.00
    (round
    -15.94
     gé
    -15.81
    邻
    -15.81
     Rounds
    -15.75
    输入
    -15.75
    -radius
    -15.50
    仓
    -15.44
    POSITIVE LOGITS
    analy
    17.00
    undry
    16.75
    分析
    16.63
    ctal
    16.38
    apur
    15.38
     Analy
    15.25
    APT
    15.06
     analysis
    15.06
    analysis
    14.81
    uned
    14.63
    Activations Density 0.015%

    No Known Activations