© 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. 65385
    Prev
    Next
    INDEX
    Explanations

    TCP 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
    å¿«æĬ¥
    -0.08
    lauch
    -0.08
    stech
    -0.08
    istring
    -0.08
     interf
    -0.07
    人èĦ¸è¯ĨåĪ«
    -0.07
    ë½ij
    -0.07
     chém
    -0.07
    ndon
    -0.07
    rint
    -0.07
    POSITIVE LOGITS
    ä¹Ĵä¹ĵ
    0.08
     맺
    0.08
    æ±Ģ
    0.07
     negotiated
    0.07
    æµģéĩı
    0.07
    åıijèµ·
    0.07
     initiator
    0.07
     packets
    0.07
     Reno
    0.07
    ilateral
    0.07
    Activations Density 0.040%

    No Known Activations