© 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. 58727
    Prev
    Next
    INDEX
    Explanations

    medical research abstracts and headings

    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
    飬
    -0.08
    æł¼å°Ķ
    -0.08
    rost
    -0.07
    é¤
    -0.07
    estyle
    -0.07
    essler
    -0.07
    yce
    -0.07
    åijĬçŁ¥ä¹¦
    -0.07
    tev
    -0.07
    rano
    -0.07
    POSITIVE LOGITS
    uples
    0.07
    微信æī«çłģ
    0.07
    jn
    0.06
    hetto
    0.06
    çķĻä½ı
    0.06
    ARE
    0.06
     Karn
    0.06
     Helm
    0.06
     lan
    0.06
     impress
    0.06
    Activations Density 0.001%

    No Known Activations