© 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. 29536
    Prev
    Next
    INDEX
    Explanations

    count of items

    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
    尤为
    -0.12
    å°¤åħ¶
    -0.11
    å°¤åħ¶æĺ¯åľ¨
    -0.10
    ç§ijæĬĢèĤ¡ä»½
    -0.10
    LayoutConstraint
    -0.09
    åIJĦè¡ĮåIJĦä¸ļ
    -0.09
    æĽ´èĥ½
    -0.09
    ç®Ģ称
    -0.09
    æĽ´æĺ¯
    -0.09
    çī¹åĪ«æĺ¯åľ¨
    -0.09
    POSITIVE LOGITS
    çİ°åŃĺ
    0.10
    лож
    0.09
    å¼ĺæī¬
    0.09
    æijĨåľ¨
    0.08
    åħ¶æīĢ
    0.08
    éĻ·
    0.08
     Cr
    0.08
    èħ¥
    0.08
    æĵĴ
    0.08
    /e
    0.08
    Activations Density 0.025%

    No Known Activations