© 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. 55055
    Prev
    Next
    INDEX
    Explanations

    We describe, report, use, develop

    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
     gotta
    -0.09
    è¦ģèµ°
    -0.09
    è¦ģ被
    -0.08
    æĪijå¾Ĺ
    -0.08
    unky
    -0.08
    è¦ģåIJĥ
    -0.08
    æķ´æĶ¹èIJ½å®ŀ
    -0.07
    inheritdoc
    -0.07
    è¾ŀæŧ
    -0.07
    æĪijä¸Ģ个人
    -0.07
    POSITIVE LOGITS
     also
    0.09
     ëĺIJíķľ
    0.08
     extensively
    0.07
    åıijçİ°åľ¨
    0.07
    注æĦıåĪ°
    0.07
     adopt
    0.07
     briefly
    0.07
     employ
    0.07
    riot
    0.07
     ÑĤакже
    0.07
    Activations Density 0.653%

    No Known Activations