© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37835
    Prev
    Next
    INDEX
    Explanations

    painting and drawing

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Zimmerman
    -0.11
    NECT
    -0.10
    ä½¼
    -0.09
    æľįåĬ¡åijĺ
    -0.09
     Manson
    -0.09
    æĨ¾
    -0.09
    楼主
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    htag
    -0.08
    éł»éģĵ
    -0.08
    POSITIVE LOGITS
    æ²¹æ¼Ĩ
    0.11
     paints
    0.10
    brush
    0.10
     painted
    0.10
     painting
    0.10
    (Paint
    0.09
    æ¶ĤæĬ¹
    0.09
     Painting
    0.09
    å¢Ļå£ģ
    0.09
    å¹ħ
    0.09
    Activations Density 0.025%

    No Known Activations