© 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. 40309
    Prev
    Next
    INDEX
    Explanations

    too many

    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
    å¾Īæĥ³
    -0.10
    大å¤ļ
    -0.10
    typ
    -0.09
    Neo
    -0.08
    大éĥ¨åĪĨ人
    -0.08
    ritos
    -0.08
     necessarily
    -0.08
    berger
    -0.08
    éĢŁ
    -0.08
    territ
    -0.08
    POSITIVE LOGITS
    ä»Ĭ天æĪij们
    0.11
    头æĿ¡
    0.10
    åıªåī©ä¸ĭ
    0.09
    åĵįèµ·
    0.09
    æĴĩ
    0.09
     headlines
    0.09
    æį¢æĪIJ
    0.09
    ä¹ŁæŃ£æĺ¯
    0.09
    åıijçĶŁäºĨ
    0.08
    çł¾
    0.08
    Activations Density 0.033%

    No Known Activations