© 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. 6229
    Prev
    Next
    INDEX
    Explanations

    work or development

    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
    笳
    -0.09
    å²Ĺ
    -0.09
     gắn
    -0.08
    è°ģçŁ¥
    -0.08
    èĢģ大
    -0.08
    UST
    -0.08
    æijĨæĶ¾
    -0.08
    åıĤ
    -0.08
    ustr
    -0.08
    讲å¸Ī
    -0.08
    POSITIVE LOGITS
    èĬ¯
    0.09
    éļ½
    0.09
    çģ¼
    0.09
    -ts
    0.08
    绯
    0.08
    åħ¬åŃIJ
    0.08
    .cut
    0.08
    å¤ıæĹ¥
    0.08
    orm
    0.08
    avr
    0.08
    Activations Density 0.002%

    No Known Activations