© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    Dean

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

    No Comments

    Negative Logits
    资本
    -23.13
     capital
    -21.38
    capital
    -19.63
    ANT
    -19.00
    (cap
    -18.88
    抗
    -18.75
     capitalize
    -18.50
     Capital
    -18.25
    REL
    -18.25
     rel
    -18.00
    POSITIVE LOGITS
     Dean
    40.75
    Dean
    38.00
     dean
    29.25
     terminal
    20.00
    条
    18.88
    终端
    18.25
     Admin
    17.00
     admin
    16.75
     det
    16.75
     Leg
    16.25
    Activations Density 0.162%

    No Known Activations