© 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. 6078
    Prev
    Next
    INDEX
    Explanations

    transactional context

    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
    çĻ½å¤©
    -0.11
    鼶è·Ŀ离
    -0.09
    楼主
    -0.09
    ç½ijæĬķ
    -0.08
    æķ¬
    -0.08
    .visualization
    -0.08
    æķĪæŀľåĽ¾
    -0.08
    รà¸ĵ
    -0.08
    åºĶæĶ¶
    -0.08
    éĤ£äºº
    -0.08
    POSITIVE LOGITS
    CEO
    0.10
     manufacturing
    0.10
    èĤ¡ä»·
    0.09
    å·¥ç¨ĭå¸Ī
    0.09
    çļĦæł¸å¿ĥ
    0.09
    æ¯ĽåĪ©çİĩ
    0.09
    åħ¨çIJĥ
    0.09
    åıijçĥ§
    0.09
     swollen
    0.09
    å¸ĤåĢ¼
    0.09
    Activations Density 0.196%

    No Known Activations