© 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. 5966
    Prev
    Next
    INDEX
    Explanations

    saying that

    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
    å·´æĭī
    -0.10
    ä¸įèµ·
    -0.10
    æĮĩåįĹ
    -0.10
    æīĢè°ĵçļĦ
    -0.10
    æijĺ
    -0.09
    æĥ³æĥ³
    -0.09
    æ¶Īæģ¯
    -0.09
     dó
    -0.09
    彪
    -0.09
    ä½łè¯´
    -0.09
    POSITIVE LOGITS
    å¾Ĺå¾Ī好
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
    æ§Ľ
    0.09
    å½ĵæĪij们
    0.09
    å¾Ĺå¾Ī
    0.08
    apon
    0.08
    è±ģ
    0.08
    稿
    0.08
    erland
    0.08
    æ©Ħæ¦Ħ
    0.08
    Activations Density 0.011%

    No Known Activations