© 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. 6281
    Prev
    Next
    INDEX
    Explanations

    people died or have

    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
    æĺ¯ä¸Ģ项
    -0.10
    åıªèĥ½è¯´
    -0.10
    å¹³åĩ¡
    -0.09
     Pills
    -0.09
    æĿ¥çļĦ
    -0.09
     rfl
    -0.09
    èľĤèľľ
    -0.09
    使åħ¶
    -0.09
    åıªæĥ³
    -0.09
    æĪijä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    丧
    0.10
    被æīĵ
    0.10
    è¯ķ
    0.10
    æĪĸå¤ļ
    0.10
    iddy
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    缴è¾ĸ
    0.09
    asar
    0.09
    _mB
    0.09
    æķ´é½IJ
    0.08
    Activations Density 0.093%

    No Known Activations