© 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. 24093
    Prev
    Next
    INDEX
    Explanations

    published within

    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
    æĮ
    -0.10
    é£İæł¼
    -0.08
    éķ°
    -0.08
    ãĤ®ãĥ£
    -0.08
     pitch
    -0.08
    æĶ¯
    -0.08
    åIJĦèĩª
    -0.08
    è´¯
    -0.08
    .Syntax
    -0.08
    gor
    -0.07
    POSITIVE LOGITS
     herein
    0.11
    寿
    0.11
    彩
    0.09
    è®°
    0.09
    è¿ĻéĩĮ
    0.09
    è¿Ļè¾¹
    0.09
    æĿ¥èĩªäºİ
    0.09
    ç¦ıéŁ³
    0.09
    åľ¨è¿ĻéĩĮ
    0.08
    伤
    0.08
    Activations Density 0.011%

    No Known Activations