© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    design and development

    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
    ç»ĻäºĪäºĨ
    -0.10
    满æĦıçļĦ
    -0.09
    Ùģرد
    -0.09
    åīį身
    -0.09
    اÙĩÙĦ
    -0.09
    åħ¨å¤©
    -0.09
    acy
    -0.09
    ä¸ĭæĿ¥çļĦ
    -0.08
    phia
    -0.08
    å½ĵäºĭ
    -0.08
    POSITIVE LOGITS
    ä¹ĭéģĵ
    0.09
    å¸Ī
    0.09
    師
    0.09
    èĢħ
    0.08
    er
    0.08
    CN
    0.08
    lesi
    0.08
    å®ĮæĪIJåIJİ
    0.08
    é¦Ĩ
    0.08
    éļĺ
    0.08
    Activations Density 0.191%

    No Known Activations