© 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. 59368
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by participles or infinitives

    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
    å¾Ī强
    -0.09
    éģĩåĪ°äºĨ
    -0.09
    åħ·
    -0.09
    èģĮä¸ļéģĵå¾·
    -0.09
    -ph
    -0.09
     Temper
    -0.09
    mor
    -0.08
     mor
    -0.08
    /logging
    -0.08
    æľīå¾Ī大çļĦ
    -0.08
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.10
    ç»ĵå°¾
    0.09
    еÑģÑĤво
    0.09
    èľĤ
    0.09
    人éĢł
    0.09
    ideo
    0.08
    æ¹¾
    0.08
    çݯç»ķ
    0.08
    被
    0.08
     Yong
    0.08
    Activations Density 0.078%

    No Known Activations