© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13987
    Prev
    Next
    INDEX
    Explanations

    say communication

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

    No Comments

    Negative Logits
    ArrayType
    -19.63
    _cap
    -19.00
    _mux
    -18.75
    Caps
    -18.38
     Caps
    -18.13
    _serialize
    -18.13
    �性
    -17.38
     caps
    -17.13
    _clusters
    -17.00
    _cluster
    -16.88
    POSITIVE LOGITS
     communication
    28.63
    沟通
    27.13
     communicate
    26.13
    对话
    26.00
     Communication
    25.63
     communicating
    25.63
    communication
    25.38
     communicated
    25.38
     communicates
    25.00
    Communication
    23.75
    Activations Density 0.715%

    No Known Activations