© 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. 9302
    Prev
    Next
    INDEX
    Explanations

    demonstrate

    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
    enate
    -0.10
    à¹īà¸Ńม
    -0.09
    ़
    -0.09
    rave
    -0.09
    alendar
    -0.09
    交çĶµ
    -0.09
    -0.08
    thon
    -0.08
    ftime
    -0.08
    WAY
    -0.08
    POSITIVE LOGITS
    گر
    0.08
    haft
    0.08
    /testify
    0.08
    s
    0.08
    ات
    0.08
    াতà§įর
    0.08
     conclus
    0.08
     adanya
    0.08
    æĸĩ稿
    0.07
    agne
    0.07
    Activations Density 0.035%

    No Known Activations