© 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. 63983
    Prev
    Next
    INDEX
    Explanations

    404 errors

    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
    è£Ķ
    -0.11
    æ®ĭçķĻ
    -0.10
    贯彻
    -0.10
    æ±ĩçİĩ
    -0.10
    æķŀå¼Ģ
    -0.10
    äºĮæīĭ
    -0.09
    åŃ«
    -0.09
    ispers
    -0.09
    沫
    -0.09
    ä¸Ĭ线
    -0.09
    POSITIVE LOGITS
     Haj
    0.10
    åŀ©
    0.09
     apolog
    0.09
    åıĭ
    0.09
    迷人
    0.09
    .cls
    0.08
     hurd
    0.08
    æĥķ
    0.08
     GT
    0.08
    occ
    0.08
    Activations Density 0.134%

    No Known Activations