© 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. 29658
    Prev
    Next
    INDEX
    Explanations

    items, phrases, or clauses connected by punctuation

    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
    åĪ«è¯´
    -0.09
    åħ¨æĺ¯
    -0.09
    éĻ
    -0.09
    åľ¨æĪijçļĦ
    -0.09
    å®Łãģ¯
    -0.09
    åľ¨æĪij
    -0.09
    说å®ŀè¯Ŀ
    -0.08
    æĴµ
    -0.08
    UREMENT
    -0.08
    æĪij没
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯åľ¨
    0.10
    对èĩªå·±çļĦ
    0.10
    é£İåIJ¹
    0.09
    å¾ĢæĿ¥
    0.08
    对èĩªå·±
    0.07
    åħ¶æīĢ
    0.07
    å¯Ĥå¯ŀ
    0.07
     ìĿ´ë¥¼
    0.07
    insky
    0.07
     Tus
    0.07
    Activations Density 0.066%

    No Known Activations