© 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. 38692
    Prev
    Next
    INDEX
    Explanations

    Internet Protocol (IP) and related 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
    VML
    -0.07
    nable
    -0.07
     подбоÑĢ
    -0.06
    udas
    -0.06
    غÙħ
    -0.06
    æĹłéĻħ
    -0.06
    æĬķèµĦä»·åĢ¼
    -0.06
    IPT
    -0.06
    SqlServer
    -0.06
    EIC
    -0.06
    POSITIVE LOGITS
    åįıè®®çļĦ
    0.11
    åįıè®®
    0.10
     Operating
    0.09
     protocols
    0.09
     protocol
    0.08
    Delivery
    0.08
     operating
    0.08
     пÑĢоÑĤо
    0.08
     Delivery
    0.08
    _send
    0.08
    Activations Density 0.079%

    No Known Activations