© 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. 24341
    Prev
    Next
    INDEX
    Explanations

    parts and components

    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
    ç¯Ļ
    -0.10
    çŁŃæļĤ
    -0.10
    æĮij
    -0.10
    æ´Ļ
    -0.09
    ç¢ij
    -0.09
    atories
    -0.09
     rowspan
    -0.09
    溢
    -0.09
    èĢĢ
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.09
    POSITIVE LOGITS
    éĥ¨ä»¶
    0.19
    鼶éĥ¨ä»¶
    0.17
    鼶件
    0.17
     parts
    0.15
     Parts
    0.13
     components
    0.13
    ç»Ħ件
    0.13
    parts
    0.12
    Parts
    0.12
    ç»ĦæĪIJéĥ¨åĪĨ
    0.11
    Activations Density 0.128%

    No Known Activations