© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12206
    Prev
    Next
    INDEX
    Explanations

    acne and breakouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    è·ĸ
    -0.10
    失èIJ½
    -0.10
    èĵĦ
    -0.10
    æ´»åĬ¨çİ°åľº
    -0.09
    è·µ
    -0.09
    饴
    -0.09
    èĸª
    -0.09
    éľĪ
    -0.09
    ä¿Ŀæļĸ
    -0.09
    ABL
    -0.09
    POSITIVE LOGITS
    çĹĺçĹĺ
    0.13
    çŤ
    0.12
     acne
    0.12
    éĿĴæĺ¥
    0.11
    åĿĬ
    0.09
    åłµå¡ŀ
    0.09
    ars
    0.09
    ç»ĨèıĮ
    0.09
    åĪĺæµ·
    0.08
     Ac
    0.08
    Activations Density 0.066%

    No Known Activations