© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27467
    Prev
    Next
    INDEX
    Explanations

    peer-to-peer networks and protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    微信æī«çłģ
    -0.09
     substitutions
    -0.09
    大类
    -0.09
     concess
    -0.08
    ä¸İçݰ代
    -0.08
     campa
    -0.08
     conversions
    -0.08
    Conversion
    -0.08
    åŃIJç±»
    -0.08
     رÙģ
    -0.08
    POSITIVE LOGITS
     peer
    0.09
    éĢļä¿¡
    0.09
     network
    0.08
    peer
    0.08
     communication
    0.08
     gossip
    0.08
     multicast
    0.08
     synchronized
    0.08
     peers
    0.08
     leader
    0.08
    Activations Density 0.123%

    No Known Activations