© 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. 6114
    Prev
    Next
    INDEX
    Explanations

    Change, All, Style, Take

    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«Ļéķ¿
    -0.10
    way
    -0.09
    为客æĪ·
    -0.09
    pany
    -0.09
    åľ¨èģĮ
    -0.09
    illet
    -0.09
    è¿IJèIJ¥ç®¡çIJĨ
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    åīįåı°
    -0.08
    .tap
    -0.08
    POSITIVE LOGITS
    æķĻä½ł
    0.10
     Tháng
    0.08
    çĭ¬å®¶
    0.08
    å®ŀçĶ¨
    0.08
    коп
    0.08
    ëĭĪê¹Į
    0.08
    çĶŁæ´»çļĦ
    0.08
    æľĢåıĹ欢è¿İ
    0.08
    åħ¬è®¤
    0.08
    enames
    0.08
    Activations Density 0.060%

    No Known Activations