© 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. 44628
    Prev
    Next
    INDEX
    Explanations

    consanguinity

    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
    åģ¶
    -0.07
     _______,
    -0.07
    èĢĮå½Ĵ
    -0.07
    aff
    -0.07
    水份
    -0.07
    erst
    -0.07
    onsor
    -0.06
    声
    -0.06
    å·´å¡ŀ
    -0.06
     âĨIJ
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģåĩĨå¤ĩ
    0.09
     realistically
    0.08
    å¤ļéķ¿æŶéĹ´
    0.08
    çļĦ人ä¼ļ
    0.08
    Formatted
    0.08
    æĺ¯åIJ¦ä¼ļ
    0.08
    æĬ¥åijĬä¼ļ
    0.07
    åĩĨå¤ĩ
    0.07
    åĽ½è´¸
    0.07
    åĩĨå¤ĩçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations