© 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. 19567
    Prev
    Next
    INDEX
    Explanations

    code definitions and function calls

    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
    æĺ¯è¦ģ
    -0.07
     güz
    -0.07
    çļĦå°±æĺ¯
    -0.07
    åIJĮæŶè¦ģ
    -0.07
     eli
    -0.07
    åĤµ
    -0.07
     Richt
    -0.06
    çļĦæĺ¯
    -0.06
    veled
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
    entemente
    0.07
     undermin
    0.07
    asInstanceOf
    0.07
    åŁİ
    0.07
    entos
    0.07
    éŨåħ³
    0.07
    ÛĮشاÙĨ
    0.07
    Scalars
    0.06
    ParseException
    0.06
    èĢ¸
    0.06
    Activations Density 0.387%

    No Known Activations