© 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. 59213
    Prev
    Next
    INDEX
    Explanations

    methamphetamine and amphetamine derivatives

    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
     fats
    -0.10
    ä¸ŃæĸŃ
    -0.09
    ÑĮ
    -0.09
    çĸµ
    -0.09
    èī¯
    -0.09
    ERVER
    -0.09
    erved
    -0.09
    otros
    -0.09
    仪
    -0.09
    éĤ£è¾¹
    -0.08
    POSITIVE LOGITS
    /thumb
    0.09
    åľ¨åħ¨åĽ½
    0.09
    çĦ¶æĺ¯
    0.09
    å¸ĮæľĽèĥ½
    0.09
    åĬ²
    0.08
    æ»ĺ
    0.08
    çĪ±åĽ½ä¸»ä¹ī
    0.08
    po
    0.08
    maker
    0.08
    é²ľæ´»
    0.08
    Activations Density 0.023%

    No Known Activations