© 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. 56857
    Prev
    Next
    INDEX
    Explanations

    abbreviations and symbols

    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
    æĸŃ
    -0.07
    æľīäºĨä¸Ģ个
    -0.07
    olf
    -0.07
    æıIJè¦ģ
    -0.07
    inas
    -0.06
    å½·
    -0.06
     Koh
    -0.06
    ()._
    -0.06
    姥
    -0.06
    athi
    -0.06
    POSITIVE LOGITS
     denotes
    0.14
     denote
    0.12
    æĦıæĮĩ
    0.11
    æĮĩçļĦæĺ¯
    0.11
     обознаÑĩа
    0.10
    æĮĩ
    0.10
     refers
    0.10
    æĦı为
    0.10
     หมายà¸ĸึà¸ĩ
    0.09
    æĺ¯æĮĩ
    0.09
    Activations Density 0.251%

    No Known Activations