© 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. 6093
    Prev
    Next
    INDEX
    Explanations

    mining company, disasters, respirable

    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
    æĥ³æĥ³
    -0.10
    åij½ä¸Ń
    -0.09
    boat
    -0.09
    _HIT
    -0.09
    åįĥæĸ¹
    -0.09
    笼
    -0.09
    åĿ¦
    -0.09
    Hint
    -0.09
    å¥ī
    -0.09
    æŁĺ
    -0.09
    POSITIVE LOGITS
    éĩĩçŁ¿
    0.14
    æİĺ
    0.13
    å¼Ģéĩĩ
    0.13
    çħ¤çŁ¿
    0.13
    æĪĴ
    0.12
     miners
    0.12
    çħ¤
    0.11
     mining
    0.11
    çŁ¿åĮº
    0.11
    çŁ¿å±±
    0.10
    Activations Density 0.088%

    No Known Activations