© 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. 19723
    Prev
    Next
    INDEX
    Explanations

    macrophage-mediated

    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
    è·Įå®ķ
    -0.08
    ä¿Ŀä½ij
    -0.07
     Conway
    -0.07
    èij«èĬ¦
    -0.07
     svil
    -0.07
    æĮ¥éľį
    -0.07
    ä¸ĩåıĺ
    -0.07
    èij«
    -0.06
    ä¸ĬåİķæīĢ
    -0.06
     verg
    -0.06
    POSITIVE LOGITS
    -mediated
    0.09
    /mac
    0.08
    leen
    0.08
     mediator
    0.08
     frontline
    0.08
    åīį身
    0.07
     mediated
    0.07
    -init
    0.07
    lect
    0.07
    ä»ĭ
    0.07
    Activations Density 0.129%

    No Known Activations