© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    do not say interface

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

    No Comments

    Negative Logits
     interface
    -41.25
     Interface
    -40.25
     interfaces
    -40.00
    接口
    -37.25
     Interfaces
    -37.00
    Interface
    -36.00
    Interfaces
    -36.00
    _Interface
    -35.00
    _INTERFACE
    -34.75
     INTERFACE
    -33.75
    POSITIVE LOGITS
    粒
    20.25
    游
    16.38
     Barton
    15.88
    _GPS
    15.19
    _gps
    14.88
     GM
    14.69
    羊
    14.63
    毓
    14.63
    歌曲
    14.38
     Grammy
    14.25
    Activations Density 0.057%

    No Known Activations