© 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. 581
    Prev
    Next
    INDEX
    Explanations

    units and dimensions

    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
    ÑĮе
    -0.10
    ä¸įæĪIJ
    -0.10
    æĥ³æĥ³
    -0.10
    å°¤åħ¶æĺ¯
    -0.09
     ведÑĮ
    -0.09
    æ¾į
    -0.09
    modx
    -0.09
    è¤IJ
    -0.09
    形象
    -0.09
    unts
    -0.09
    POSITIVE LOGITS
    äºĨæĪijçļĦ
    0.09
    æĭĶ
    0.08
     ÑĤÑĢÑĥд
    0.08
    /am
    0.08
    rimp
    0.07
    æĭ§
    0.07
    æĸĩ娱
    0.07
    ä¸ī级
    0.07
    åħ¨åĬĽ
    0.07
     rem
    0.07
    Activations Density 0.142%

    No Known Activations