© 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. 26243
    Prev
    Next
    INDEX
    Explanations

    incapacitate, knockout, disorient

    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
    Õ³
    -0.10
    å·§
    -0.10
    åĿŀ
    -0.10
    å¥ķ
    -0.09
    åħĪè¿Ľåįķä½į
    -0.09
    åħij
    -0.09
    å¤įæŁ¥
    -0.09
    æ¾İæ¹ĥ
    -0.09
    åľ¨åĨħçļĦ
    -0.09
    æī§æĦı
    -0.09
    POSITIVE LOGITS
    ä¸įåĬ¨
    0.12
    æ°Ķä½ĵ
    0.09
    åī¥å¤º
    0.09
     Breath
    0.09
    æĪª
    0.09
    带ä¸Ĭ
    0.09
    æīĵæ³ķ
    0.08
     incapac
    0.08
    .flatten
    0.08
    ç«ĭ
    0.08
    Activations Density 0.067%

    No Known Activations