© 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. 568
    Prev
    Next
    INDEX
    Explanations

    religious or political affiliations or groups

    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
    使çĶ¨èĢħ
    -0.11
    sist
    -0.09
    主任
    -0.09
    è¹Ī
    -0.09
    使çĶ¨èĢħæĪĸ
    -0.09
    ILD
    -0.09
    太平
    -0.09
    ä¸įåIJĮç±»åŀĭ
    -0.09
    ride
    -0.09
    heet
    -0.09
    POSITIVE LOGITS
    们
    0.15
    们çļĦ
    0.14
    åĢij
    0.14
    innen
    0.13
    们éĥ½
    0.11
    sWith
    0.11
    ÑģÑĤво
    0.11
    esco
    0.11
    swith
    0.10
    ëĵ¤ëıĦ
    0.10
    Activations Density 0.128%

    No Known Activations