© 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. 40324
    Prev
    Next
    INDEX
    Explanations

    tax and payment obligations

    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
    åĩºåħ¥
    -0.09
    åįĩéĻį
    -0.09
    ä¸ŃåİŁ
    -0.09
     ÑĥÑģп
    -0.09
    ä¸īæľŁ
    -0.08
    å·²æľī
    -0.08
    èIJģ
    -0.08
    .wh
    -0.08
    enes
    -0.08
    åĩºéģĵ
    -0.08
    POSITIVE LOGITS
    缴纳
    0.12
    ç¹³
    0.10
    dg
    0.10
    社ä¼ļ责任
    0.09
    ãĥĵãĥ¥ãĥ¼
    0.09
    çīĸ
    0.09
    GOR
    0.09
    æŀ¶åŃIJ
    0.09
    hta
    0.09
    æŀķ
    0.09
    Activations Density 0.031%

    No Known Activations