© 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. 21877
    Prev
    Next
    INDEX
    Explanations

    scrolls down

    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
    oref
    -0.09
    дови
    -0.08
    opoly
    -0.08
    ×ŀר
    -0.08
    Ñģпи
    -0.08
    _qs
    -0.08
    oncini
    -0.08
    òi
    -0.07
    커
    -0.07
    عÙģ
    -0.07
    POSITIVE LOGITS
    è¿Ļåı«
    0.20
    称为
    0.19
    被称为
    0.17
     tzv
    0.16
     tzw
    0.16
    ãģĦãĤıãĤĨãĤĭ
    0.15
     sogenannte
    0.15
    åı«åģļ
    0.15
     Called
    0.15
    称ä¹ĭ为
    0.14
    Activations Density 0.935%

    No Known Activations