© 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. 60086
    Prev
    Next
    INDEX
    Explanations

    cosmetic surgery and treatments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æľĹæľĹ
    -0.08
    è¯Ĩ
    -0.08
    秣
    -0.08
    é£
    -0.07
    åĸĺæģ¯
    -0.07
    æĬĦ
    -0.07
     Assembly
    -0.06
    undry
    -0.06
    æīĭæĬĦæĬ¥
    -0.06
    Inspectable
    -0.06
    POSITIVE LOGITS
     implants
    0.10
    审ç¾İ
    0.09
     candidacy
    0.09
    å¾®åĪĽ
    0.09
    راØŃ
    0.08
     aesthetic
    0.08
    oker
    0.08
    ä¸Ĭçĺ¾
    0.08
    ç¾İåѦ
    0.08
     Implant
    0.08
    Activations Density 0.226%

    No Known Activations