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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    青砖

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

    No Comments

    Negative Logits
    砖
    -25.13
     Marble
    -21.63
     brick
    -20.75
     bricks
    -20.00
    brick
    -19.25
     Brick
    -18.88
    phinx
    -18.13
    蜣
    -18.13
    _tiles
    -17.25
     marble
    -17.13
    POSITIVE LOGITS
    太原
    20.63
    山西
    17.75
    政策
    17.38
     policy
    17.13
    ᾱ
    17.00
     Policy
    16.88
    日军
    16.75
    _logger
    16.63
     policies
    16.50
    动画
    16.25
    Activations Density 0.235%

    No Known Activations