© 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. 60687
    Prev
    Next
    INDEX
    Explanations

    CMS, Medicare, Medicaid, Anthem, Realty

    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
    æĸ°å¢ŀ
    -0.09
    éľĩ
    -0.09
    getNode
    -0.08
    æĺ§
    -0.08
    形象
    -0.08
    åĺ´å·´
    -0.08
    ingham
    -0.08
    çĥŃè¡Ģ
    -0.08
    anda
    -0.08
    æ¦Ħ
    -0.08
    POSITIVE LOGITS
    åĵ¡
    0.10
    æ·Ģ
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
    ç§ģç«ĭ
    0.09
    åľ¨èģĮ
    0.09
    å¸ĮæľĽ
    0.09
    /effects
    0.08
    åijĺ
    0.08
    æĶ¶è´Ń
    0.08
    0.08
    Activations Density 0.004%

    No Known Activations