© 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. 35026
    Prev
    Next
    INDEX
    Explanations

    programming interfaces

    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
    1
    -0.06
    R
    -0.06
    ç·©
    -0.06
    2
    -0.06
    itt
    -0.06
    iges
    -0.06
    æ¥Ķ
    -0.06
    ึà¸ģ
    -0.06
    ä¼Ļ
    -0.06
    -
    -0.06
    POSITIVE LOGITS
    æīĢå±ŀåĪĨç±»
    0.09
    евиÑĩ
    0.09
    å¥Īä½ķ
    0.09
    æ´»åĬ¨åĩĨå¤ĩ
    0.08
    åį´ä¸įèĥ½
    0.08
    微信æī«çłģ
    0.08
    timeofday
    0.08
     алÑİми
    0.08
     меÑĤаллиÑĩ
    0.08
    urgeon
    0.08
    Activations Density 0.001%

    No Known Activations