© 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. 832
    Prev
    Next
    INDEX
    Explanations

    makeup and beauty products

    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
    ายà¸Ļ
    -0.11
    绳
    -0.10
    WithValue
    -0.10
    ä»ĸåľ¨
    -0.10
    egend
    -0.10
    足足
    -0.10
    //{{
    -0.10
    éŁ¿
    -0.09
    _CALC
    -0.09
    chers
    -0.09
    POSITIVE LOGITS
    å¦Ĩ
    0.11
    åĮĸå¦Ĩ
    0.10
     ná»ģn
    0.09
     makeup
    0.09
    ç²
    0.08
    ä»ĺãģij
    0.08
    åĬŀ
    0.08
    åĮĸåѦåĵģ
    0.08
    æł¹åŁº
    0.08
    åĶĩ
    0.08
    Activations Density 0.071%

    No Known Activations