© 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. 29475
    Prev
    Next
    INDEX
    Explanations

    pay and conditions

    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
    åģľå·¥
    -0.09
    å¤ļå±Ĥ次
    -0.09
    rador
    -0.09
    åĬłå¤§
    -0.09
    æķĻåŃ¦è´¨éĩı
    -0.08
    ä¸įäºĨ
    -0.08
    è¨Ģ
    -0.08
    è··
    -0.08
    naire
    -0.08
    heck
    -0.08
    POSITIVE LOGITS
    ings
    0.10
    åĴĮæľįåĬ¡
    0.10
    æĢ»é¢Ŀ
    0.09
    æ¦
    0.09
    bee
    0.09
    çµ²
    0.09
     Zhu
    0.08
    heets
    0.08
    rier
    0.08
    .setEditable
    0.08
    Activations Density 0.009%

    No Known Activations