© 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. 24113
    Prev
    Next
    INDEX
    Explanations

    pottery and handicrafts

    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¨ģåĬĽ
    -0.11
    çĸŁ
    -0.10
    ä¼Ļ
    -0.09
    æ´½
    -0.09
    æįĨ
    -0.09
    ToolStrip
    -0.09
     Shuffle
    -0.09
    åħ¥åľº
    -0.09
    èĿĹ
    -0.09
    /Layout
    -0.09
    POSITIVE LOGITS
    éĩī
    0.13
     pottery
    0.13
    çªij
    0.12
    å·¥ä½ľå®¤
    0.11
    çĵ·åĻ¨
    0.11
    éĻ¶çĵ·
    0.11
    åŃĺ
    0.10
    åĮł
    0.10
    éĻ¶
    0.10
    æ³¥åľŁ
    0.10
    Activations Density 0.054%

    No Known Activations