© 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. 44415
    Prev
    Next
    INDEX
    Explanations

    relationship satisfaction duration

    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
    ness
    -0.07
    æĮĩå®ļåľ°çĤ¹
    -0.07
    ils
    -0.07
    èIJ½å¯ŀ
    -0.07
    жина
    -0.06
     koj
    -0.06
    åĪĹ
    -0.06
    æ¸ħç§Ģ
    -0.06
    å¨ĺ
    -0.06
    fox
    -0.06
    POSITIVE LOGITS
    è£ĤçĹķ
    0.10
    磨åIJĪ
    0.09
     dynamics
    0.09
    åħ±åIJĮæĪIJéķ¿
    0.08
     waarin
    0.08
    æľŁä¸Ń
    0.08
     partners
    0.08
    ä¸ŃçļĦæķ°æį®
    0.08
    umah
    0.08
    éķ¿ä¹ħçļĦ
    0.08
    Activations Density 0.067%

    No Known Activations