© 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. 40329
    Prev
    Next
    INDEX
    Explanations

    immune system

    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¡Ģèħ¥
    -0.09
    illion
    -0.08
    æĥĬå¿ĥ
    -0.08
    ä¸įåı¯æĢķ
    -0.08
    羣çĪ±
    -0.08
    羣åģĩ
    -0.07
     tact
    -0.07
     تÙĨد
    -0.07
    ä½ľä¸ļ
    -0.07
    utorial
    -0.07
    POSITIVE LOGITS
     health
    0.14
    åģ¥åº·
    0.14
    health
    0.13
    åģ¥åº·çļĦ
    0.13
    æĬµæĬĹåĬĽ
    0.12
    强åģ¥
    0.12
    Health
    0.11
     Health
    0.11
    -health
    0.11
    åģ¥åº·åĴĮ
    0.11
    Activations Density 0.124%

    No Known Activations