© 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. 12433
    Prev
    Next
    INDEX
    Explanations

    pronouns (us, me, you)

    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
    ynos
    -0.11
    Carrier
    -0.09
     Carrier
    -0.09
    åIJĨ
    -0.09
    äºĨä¸Ģä¼ļ
    -0.09
    æīĺ管
    -0.09
    ç»ĻåĪ«äºº
    -0.09
     carrier
    -0.09
    carrier
    -0.09
    Ø«
    -0.09
    POSITIVE LOGITS
    æĬ
    0.09
    éľĸ
    0.09
    ä¸Ģçīĩ
    0.09
    hone
    0.08
    uter
    0.08
    åµ
    0.08
    宫
    0.08
     stuff
    0.08
    ä¸Ģ个å°ı
    0.08
    wards
    0.08
    Activations Density 0.014%

    No Known Activations