© 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. 49358
    Prev
    Next
    INDEX
    Explanations

    Greek or foreign language text

    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
    ondi
    -0.08
    izzi
    -0.07
    iland
    -0.07
    ÙĦاÙĦ
    -0.07
    OrCreate
    -0.07
     Wenger
    -0.07
    åŃ¦å·¥
    -0.07
    uada
    -0.07
    erma
    -0.07
     latter
    -0.07
    POSITIVE LOGITS
    第ä¸ĢæŃ¥
    0.07
    ington
    0.07
    çļĦ第ä¸ĢæŃ¥
    0.07
    é¦ĸåħĪ
    0.07
    é¦ĸåħĪæĺ¯
    0.07
     firstly
    0.07
    à¸Ĥัà¹īà¸Ļ
    0.07
    æ²
    0.06
    ابت
    0.06
     step
    0.06
    Activations Density 0.003%

    No Known Activations