© 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. 59331
    Prev
    Next
    INDEX
    Explanations

    appeal or leave

    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
    ä¸ĢæŶ
    -0.10
    esa
    -0.09
    åħ¨æł¡
    -0.09
    ered
    -0.09
    å¥ĭæĪĺ
    -0.09
    æĹ¥åIJİ
    -0.08
    åĽºä½ĵ
    -0.08
    头顶
    -0.08
    ç¡®
    -0.08
    èĵĿ天
    -0.08
    POSITIVE LOGITS
    çķĻè¨ĢæĿ¿
    0.10
     badges
    0.10
    æĤ£
    0.09
    é¡ĺ
    0.09
    æĸĭ
    0.08
    sites
    0.08
    acy
    0.08
    踢
    0.08
    æĴ¤
    0.08
    _SITE
    0.08
    Activations Density 0.115%

    No Known Activations