© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42519
    Prev
    Next
    INDEX
    Explanations

    network structures and communication 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
    æ¯Ķåݻ年åIJĮæľŁ
    -0.08
    çijŀæĭī
    -0.08
     exceptionnel
    -0.08
    梱
    -0.07
    æģº
    -0.07
    è®°èĢħä»İ
    -0.07
     زر
    -0.07
    ServletRequest
    -0.07
    åĪĺ家
    -0.07
    ë¡Ŀ
    -0.07
    POSITIVE LOGITS
    åĶ¯
    0.08
    æ¯ı个
    0.07
    mers
    0.07
     assignments
    0.07
    æĤĶ
    0.06
    伪
    0.06
     assignment
    0.06
     pseud
    0.06
    åIJİæĤĶ
    0.06
     constraints
    0.06
    Activations Density 0.002%

    No Known Activations