© 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. 29606
    Prev
    Next
    INDEX
    Explanations

    ignoring uncertainty

    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
    åıijçĶŁäºĨ
    -0.10
    æľīçĿĢ
    -0.10
    åıĪ被
    -0.09
    æľºèĥ½
    -0.09
     PANEL
    -0.09
    çĺ¥
    -0.09
    åĻ¤
    -0.08
    ÑĪиб
    -0.08
    ÙĦÙī
    -0.08
    å¼¥
    -0.08
    POSITIVE LOGITS
    orm
    0.11
    æĮº
    0.09
    åĪĽéĢł
    0.09
    AndView
    0.09
    æĬĬ
    0.08
    eur
    0.08
    ä½ķåĨµ
    0.08
    ä¼¼çļĦ
    0.08
    æİĴéĻ¤
    0.08
    æĶĢ
    0.08
    Activations Density 1.228%

    No Known Activations