© 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. 47652
    Prev
    Next
    INDEX
    Explanations

    texture, colors, and shapes

    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
     rais
    -0.09
    å¼ıçļĦ
    -0.09
    çĶ°
    -0.09
    éĤ£æł·
    -0.08
    hex
    -0.08
    é»ĺ
    -0.08
    rais
    -0.08
    顺便
    -0.08
    vironment
    -0.08
    身ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æĦıæĥ³ä¸įåĪ°
    0.11
    大èĥĨ
    0.10
    ORT
    0.09
    å¤ļå±Ĥ次
    0.09
    pty
    0.09
    çģ«çĤ¬
    0.09
    对è¯Ŀ
    0.09
    é¹Ĭ
    0.08
    ç´§æī£
    0.08
    åľ¨æ¸¸æĪıä¸Ń
    0.08
    Activations Density 0.053%

    No Known Activations