© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    mates and partners

    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
    çļĭ
    -0.09
    ób
    -0.08
    Levels
    -0.08
    æĩ·
    -0.08
    åıªä¸º
    -0.08
    å¤ĩæ¡Ī
    -0.08
    æī§
    -0.08
    Keyword
    -0.08
     sucker
    -0.08
    èŀį
    -0.08
    POSITIVE LOGITS
    ä¼Ļä¼´
    0.31
    åIJĪä½ľä¼Ļä¼´
    0.26
    åIJĮä¼´
    0.24
     partner
    0.23
    åIJĮäºĭ
    0.22
    æĪĺåıĭ
    0.22
    ä¼´ä¾£
    0.22
    éĤ»å±ħ
    0.21
     partners
    0.21
    éĺŁåıĭ
    0.21
    Activations Density 0.161%

    No Known Activations