© 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. 6136
    Prev
    Next
    INDEX
    Explanations

    customer service representative

    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
    rollo
    -0.09
    ROL
    -0.09
    printStats
    -0.08
    æŃ¥æŃ¥
    -0.08
    å¸Ĥå§Ķ书记
    -0.08
    æī¿è½½
    -0.08
    egt
    -0.08
    对æĪij说
    -0.08
    åĮĨ
    -0.08
    iphy
    -0.08
    POSITIVE LOGITS
    çĶ°éĩİ
    0.10
    å°±è¿ij
    0.10
    详ç»ĨäºĨ解
    0.09
    ä¼ļåıijçĶŁ
    0.09
    ijľ
    0.09
    便ä¼ļ
    0.09
    éĢµ
    0.09
     Damon
    0.08
    atif
    0.08
    åIJIJ
    0.08
    Activations Density 0.020%

    No Known Activations