© 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. 40290
    Prev
    Next
    INDEX
    Explanations

    oil industry

    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
    bery
    -0.09
    ÑĤелÑĮ
    -0.09
     gig
    -0.08
    ifa
    -0.08
    æ¿Ģ
    -0.08
    说çļĦæĺ¯
    -0.08
    æIJŃ
    -0.08
    ç´«
    -0.08
     mam
    -0.08
    æ¶
    -0.08
    POSITIVE LOGITS
     industry
    0.12
    è¡Įä¸ļä¸Ń
    0.12
     Brace
    0.12
    è¿Ļ个è¡Įä¸ļ
    0.11
    industry
    0.11
    è¡Įä¸ļçļĦ
    0.11
    è¡Įä¸ļ
    0.11
    odiac
    0.11
     industries
    0.10
    è¡Įæ¥Ń
    0.10
    Activations Density 0.145%

    No Known Activations