© 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. 26190
    Prev
    Next
    INDEX
    Explanations

    a point

    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
     Rockefeller
    -0.10
    çļĦéĤ£ç§į
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    ilated
    -0.09
    çĶ¨æĿ¥
    -0.09
    ãģĿãģĨãģĦãģĨ
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    æľĢç¾İ
    -0.08
    åĪĨéĴŁåIJİ
    -0.08
    çĴĩ
    -0.08
    POSITIVE LOGITS
     ras
    0.09
     vengeance
    0.09
    erman
    0.08
    ä¸ľæµ·
    0.08
    ray
    0.08
    æŁ¬
    0.08
    ä»ĸèĩªå·±
    0.08
    èĩªèº«çļĦ
    0.08
    rive
    0.08
    èĩªå·±
    0.08
    Activations Density 0.042%

    No Known Activations