© 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. 4335
    Prev
    Next
    INDEX
    Explanations

    scientific and medical suffixes

    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
     Thumb
    -0.08
    Thumb
    -0.07
    etty
    -0.07
     Hobby
    -0.07
    yna
    -0.06
    çļĦæīĭæĮĩ
    -0.06
    å¼Ģ端
    -0.06
    ipped
    -0.06
    ())[
    -0.06
    esan
    -0.06
    POSITIVE LOGITS
    é³Į
    0.08
    就差
    0.07
    veli
    0.07
    portes
    0.07
    емов
    0.07
    <pre
    0.07
     trám
    0.07
    ovin
    0.07
    lox
    0.07
    Ī¬
    0.07
    Activations Density 0.007%

    No Known Activations