© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61869
    Prev
    Next
    INDEX
    Explanations

    first time

    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
    ota
    -0.07
    èĨĢ
    -0.07
    åŃ¦ä¹łæķĻèĤ²
    -0.07
    uas
    -0.06
    assel
    -0.06
    ÙĩاÛĮÛĮ
    -0.06
    leans
    -0.06
    åıĹçĽĬåĮªæµħ
    -0.06
    ru
    -0.06
    绢
    -0.06
    POSITIVE LOGITS
    yce
    0.08
     Temb
    0.07
    úp
    0.07
     Kapoor
    0.07
    лиÑĤ
    0.07
    (QtCore
    0.07
    åĪĺæĻĵ
    0.07
    stal
    0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼
    0.07
    ergy
    0.07
    Activations Density 0.042%

    No Known Activations