© 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. 24193
    Prev
    Next
    INDEX
    Explanations

    internet technologies and projects

    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
    ä¸Ńå¤ĸ
    -0.11
    åģļå·¥
    -0.10
    ç»ıéªĮ丰å¯Į
    -0.10
    çĶŁäº§æĢ»
    -0.10
    åľ©
    -0.09
    ä¸ĢåIJij
    -0.09
    è¿İ
    -0.09
    ä¸ĢæĬĬ
    -0.09
    åĬĽæ±Ĥ
    -0.09
    åIJijè®°èĢħ
    -0.09
    POSITIVE LOGITS
    计ç®Ĺæľº
    0.10
     founders
    0.10
    åĽ´å¢Ļ
    0.09
    Ethernet
    0.09
    å®ħ
    0.09
    产ä¸ļåĮĸ
    0.09
    è¹ij
    0.09
     ëĭ¹ìĭľ
    0.09
    åĪĽå§ĭ人
    0.09
    4
    0.09
    Activations Density 0.173%

    No Known Activations