© 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. 526
    Prev
    Next
    INDEX
    Explanations

    body parts and clothing

    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
    对å¾ħ
    -0.07
     ÙĪاÙĨ
    -0.06
    åĴ±
    -0.06
    èĤļåŃIJéĩĮ
    -0.06
    èĩªèº«
    -0.06
    ouncil
    -0.06
    缸è§ģ
    -0.06
    çĵ¦å°Ķ
    -0.06
    .spotify
    -0.06
    antan
    -0.06
    POSITIVE LOGITS
    alias
    0.08
    stub
    0.08
    çĶŁçĶŁ
    0.07
     Ùħبار
    0.07
    è¦ģ害
    0.07
     inplace
    0.07
    gage
    0.07
    å·¥ä½ľå¼Ģå±ķ
    0.06
    å·²ç»ıå¼Ģå§ĭ
    0.06
    è¿IJè¡ĮçļĦ
    0.06
    Activations Density 0.087%

    No Known Activations