© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    say unit

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

    No Comments

    Negative Logits
     Ryan
    -17.13
    -lat
    -16.38
    _ROM
    -16.13
    晁
    -16.13
    gia
    -15.94
     VIN
    -15.75
    武士
    -15.75
     Ethan
    -15.31
     board
    -15.31
     Walsh
    -15.19
    POSITIVE LOGITS
     unit
    19.13
    大队
    17.88
    unità
    17.00
    广州市
    16.38
    Unit
    15.38
    岐
    15.25
     units
    15.19
    tober
    15.00
    -unit
    15.00
    unit
    14.94
    Activations Density 0.192%

    No Known Activations