© 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. 60564
    Prev
    Next
    INDEX
    Explanations

    cost savings and improvements

    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
    æ´
    -0.09
    æ¦Ĩ
    -0.09
    æī¿æİ¥
    -0.08
    æ·Ģ
    -0.08
    å®ĹæķĻ
    -0.08
    æ£Ģçĸ«
    -0.08
    cht
    -0.08
    Nib
    -0.08
    .annotation
    -0.08
     Beste
    -0.08
    POSITIVE LOGITS
    éĻįä½İæĪIJæľ¬
    0.14
    æĶ¹åĸĦ
    0.13
    èĬĤçľģ
    0.12
    åĩıå°ij
    0.11
    åĩıæİĴ
    0.11
     savings
    0.11
    èĬĤ约
    0.11
     improvements
    0.11
    Impro
    0.11
    æĺ¾èijĹ
    0.10
    Activations Density 0.280%

    No Known Activations