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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16368
    Prev
    Next
    INDEX
    Explanations

    say "de"

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

    No Comments

    Negative Logits
    _Pr
    -18.25
    复习
    -16.63
    -pr
    -16.13
    热水
    -16.13
    ILED
    -16.13
     confinement
    -15.75
     Burns
    -15.50
    监狱
    -15.38
    春节
    -15.38
     KeyCode
    -15.19
    POSITIVE LOGITS
     Dek
    20.00
    De
    18.13
    (de
    17.50
    vtk
    17.38
    de
    17.13
    .cy
    17.00
    Ant
    16.50
    天河
    15.94
    梭
    15.94
     Deb
    15.94
    Activations Density 0.751%

    No Known Activations