© 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. 60771
    Prev
    Next
    INDEX
    Explanations

    verbs of speaking or writing

    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
    éĿŀ常æĺİæĺ¾
    -0.10
    ä¹ĭä½ľ
    -0.09
    Attrs
    -0.09
     dele
    -0.08
     supposedly
    -0.08
    ä¿¡æģ¯æľįåĬ¡
    -0.08
    سط
    -0.08
    çļĦæĥħåĨµä¸ĭ
    -0.08
    äºĨåIJĹ
    -0.08
    说çļĦè¯Ŀ
    -0.08
    POSITIVE LOGITS
    ï¼ļ"
    0.12
    ï¼ļ
    0.11
    :&
    0.10
    ï¼ļ“
    0.10
    ï¼ļ↵
    0.10
    ï¼ļ%
    0.10
    :
    0.10
    IndexOf
    0.09
    blob
    0.09
    :`
    0.09
    Activations Density 0.057%

    No Known Activations