© 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. 16344
    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
    opoly
    -16.75
    cala
    -16.63
    appendChild
    -16.50
    leet
    -16.00
    木地板
    -15.38
    投保
    -15.25
     Theft
    -14.69
    rez
    -14.63
    TableName
    -14.50
     Zion
    -14.50
    POSITIVE LOGITS
     communication
    56.50
     Communication
    51.75
     communications
    50.25
     communicating
    50.25
     communic
    50.25
    communication
    50.00
     communicate
    49.50
     communicator
    49.00
    communic
    49.00
    通信
    48.75
    Activations Density 0.308%

    No Known Activations