© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44646
    Prev
    Next
    INDEX
    Explanations

    childlike or positive descriptors

    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
    Negative Logits
    ä»įåľ¨
    -0.07
    ä½ķç§į
    -0.07
    ستÙĩ
    -0.07
    ä½ķå¿ħ
    -0.07
    平庸
    -0.07
    irth
    -0.07
    çĮĽçĦ¶
    -0.07
    ä»įå¤Ħäºİ
    -0.07
    ä¹Łç½¢
    -0.07
    æĮģ
    -0.07
    POSITIVE LOGITS
    å°ıæľĭåıĭ们
    0.10
    å°ıæľĭåıĭ
    0.09
    ä¸įå¼Ģå¿ĥ
    0.09
     yummy
    0.09
    ä¹ĸ
    0.09
     naughty
    0.09
     Ú©ÙĪÚĨ
    0.09
    ãģĦãģ£ãģ±ãģĦ
    0.09
    大大çļĦ
    0.09
     pretend
    0.09
    Activations Density 0.490%

    No Known Activations