© 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. 59785
    Prev
    Next
    INDEX
    Explanations

    which, before, after, by

    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
    ÙĪر
    -0.07
    å¹²
    -0.07
    ÙĪرÙĬØ©
    -0.06
    å¸Ī
    -0.06
    лив
    -0.06
    las
    -0.06
    è¿Ļä¸įæĺ¯
    -0.06
    jav
    -0.06
    cest
    -0.06
    akra
    -0.06
    POSITIVE LOGITS
    ponde
    0.07
    翼翼
    0.07
    staff
    0.07
     createState
    0.07
    ç¼®
    0.07
    çıŃéĩĮ
    0.07
     misk
    0.07
    èĬ±çµ®
    0.07
    磨åIJĪ
    0.07
    æŃ¤èµ·
    0.07
    Activations Density 0.002%

    No Known Activations