© 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. 59365
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles/nouns

    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
    å¸ħ
    -0.10
    çĹĽçĤ¹
    -0.09
    åľ¨äºİ
    -0.09
    icher
    -0.08
    æĬĺå°Ħ
    -0.08
    encoding
    -0.08
    æĶ¾åĩº
    -0.08
    argo
    -0.08
    æ¥ŀ
    -0.08
    gether
    -0.08
    POSITIVE LOGITS
    æĿ¥åĪ°
    0.10
    æĻ¯è§Ĥ
    0.10
    éĹ·
    0.09
    æĿ¥èĩª
    0.09
    墩
    0.09
     kepada
    0.09
    åĪ°æľĢåIJİ
    0.09
    rys
    0.09
    åĪ°
    0.09
    æĿ¥åĪ°äºĨ
    0.09
    Activations Density 0.300%

    No Known Activations