© 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. 63981
    Prev
    Next
    INDEX
    Explanations

    "In the"

    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
    缸åħ³
    -0.17
    à¹Ģà¸Ĥา
    -0.15
    缸åħ³äººåijĺ
    -0.14
    éĤ£ç§į
    -0.13
    åij³éģĵ
    -0.13
     notion
    -0.12
    ä¸Ģå®ļç¨ĭ度
    -0.11
    æĦıä¹īä¸ĬçļĦ
    -0.11
    è§Ĵèī²
    -0.11
    缸åħ³è§Ħå®ļ
    -0.10
    POSITIVE LOGITS
     sorts
    0.14
    à¹ģà¸ĸม
    0.10
    -course
    0.10
     ×ķש׾
    0.10
     cải
    0.09
    course
    0.09
     course
    0.09
     interest
    0.09
    zelf
    0.09
    âĶŀ
    0.09
    Activations Density 0.446%

    No Known Activations