© 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. 47465
    Prev
    Next
    INDEX
    Explanations

    past participle verb

    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
    æĸ§
    -0.09
    etch
    -0.09
    å¤ļäºĨ
    -0.09
    åįĹè·¯
    -0.09
    /animations
    -0.09
    ä¸ĢæŃ¥
    -0.08
    åĴIJ
    -0.08
    æ°¸æģĴ
    -0.08
    ä»įçĦ¶æĺ¯
    -0.08
    åľ¨è¿Ļ个
    -0.08
    POSITIVE LOGITS
     ÑĢанее
    0.15
     earlier
    0.14
    åľ¨æѤä¹ĭåīį
    0.13
    åħĪåīį
    0.13
     previously
    0.12
     ÑĢанÑĮÑĪе
    0.12
     wczeÅĽniej
    0.12
    ä¹ĭåīį
    0.11
    æѤåīį
    0.11
     Earlier
    0.10
    Activations Density 0.104%

    No Known Activations