© 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. 65053
    Prev
    Next
    INDEX
    Explanations

    numbers, years, and values

    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
    azzo
    -0.07
    ibe
    -0.07
    æ´ŀåºŃ
    -0.06
    è¦ģä¹Ī
    -0.06
    åIJİèĢħ
    -0.06
     تÙĤرÙĬب
    -0.06
     itself
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    åįİå±±
    -0.06
    æĺ¯ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    çľĭçľĭåIJ§
    0.08
    åĭĻ
    0.08
    å°±ä¼ļåıijçİ°
    0.08
     recul
    0.08
    åIJİåıijçİ°
    0.08
    ä¼ļåıijçİ°
    0.07
    æ¯Ķå¦Ĥ
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    guna
    0.07
    éĻ¸çºĮ
    0.07
    Activations Density 0.003%

    No Known Activations