© 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. 699
    Prev
    Next
    INDEX
    Explanations

    necessity

    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
    æĤ²æ¬¢
    -0.08
     anonymously
    -0.08
     Ans
    -0.08
     suspense
    -0.07
    utam
    -0.07
    caffold
    -0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    поÑĢÑĤ
    -0.07
    宣读äºĨ
    -0.07
    =yes
    -0.07
    POSITIVE LOGITS
     careful
    0.10
    æł¼å¤ĸ
    0.09
    ä¸įçĦ¶
    0.09
    é¢Ŀå¤ĸçļĦ
    0.09
    åIJ¦åĪĻ
    0.08
    è¿ĺ好
    0.08
    é¢Ŀå¤ĸ
    0.08
    åĬłä»¥
    0.08
    rob
    0.08
     somehow
    0.08
    Activations Density 0.126%

    No Known Activations