© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    理念

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

    No Comments

    Negative Logits
     Seg
    -23.88
    Segments
    -22.50
    Segment
    -22.00
    段
    -21.75
    Seg
    -21.75
    _segment
    -21.50
    (segment
    -21.25
    segment
    -21.00
    注
    -20.50
     segments
    -20.25
    POSITIVE LOGITS
    理念
    22.75
     Mill
    21.38
    mill
    21.25
     mill
    20.63
    Mill
    20.00
     MILL
    18.50
     mills
    17.13
     modal
    16.38
    亿
    15.81
    .ERR
    15.63
    Activations Density 0.044%

    No Known Activations