© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by React

    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
    åħħ
    -0.08
    åĽĽäºĶ
    -0.08
    éĥĩ
    -0.08
    æł¸å®ŀ
    -0.08
    IfExists
    -0.08
    ught
    -0.07
    æĥħ人
    -0.07
    ä¸ĢçĤ¹çĤ¹
    -0.07
    ãģªãĤĵãģĭ
    -0.07
    åĽ½ç±į
    -0.07
    POSITIVE LOGITS
    忽çķ¥äºĨ
    0.10
    çĸ¥
    0.10
    è°
    0.10
    YTE
    0.09
     Helmet
    0.09
    IFF
    0.09
    èĵĿåĽ¾
    0.09
    对ä¼ģä¸ļ
    0.09
    èĪ«
    0.09
    antry
    0.09
    Activations Density 1.044%

    No Known Activations