© 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. 24194
    Prev
    Next
    INDEX
    Explanations

    vehicles, car, hardware, educational, arts, material

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.10
    éģĦ
    -0.09
    为ä¹ĭ
    -0.09
    è´§æŀ¶
    -0.09
    åĽ½èµĦå§Ķ
    -0.09
    omed
    -0.09
    hib
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    ISH
    -0.08
    leet
    -0.08
    POSITIVE LOGITS
     Mystic
    0.08
    å°¤åħ¶æĺ¯
    0.08
    èĩªæķij
    0.08
    æĺŁçIJĥ
    0.08
    ÙħÙĨاط
    0.08
    çĽ²
    0.08
    åĪ¸
    0.08
    mlink
    0.08
    ìĭŃ
    0.08
    åħ¥å¸Ĥ
    0.08
    Activations Density 1.667%

    No Known Activations