© 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. 7513
    Prev
    Next
    INDEX
    Explanations

    American or European origins

    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
    åIJij社ä¼ļ
    -0.11
    åį«åģ¥
    -0.10
    .ua
    -0.09
    ierz
    -0.08
     Aleppo
    -0.08
    åĴĮ社ä¼ļ
    -0.08
    ãĤªãĤ¹
    -0.08
     Raqqa
    -0.08
    èĢģé¾Ħ
    -0.08
    auled
    -0.08
    POSITIVE LOGITS
    æľ¬åĽ½
    0.23
    ä¸¤åĽ½
    0.23
    åħ¶ä»ĸåĽ½å®¶
    0.23
    æµ·å¤ĸ
    0.23
    è·¨åĽ½
    0.22
    åĽ½å¤ĸ
    0.21
    å¤ĸåĽ½
    0.21
    åľ¨åĽ½å¤ĸ
    0.20
    å¤ĸç±į
    0.20
    åĽŀåĽ½
    0.20
    Activations Density 0.446%

    No Known Activations