© 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. 12324
    Prev
    Next
    INDEX
    Explanations

    sufficient

    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
    æľ¬è´¨ä¸Ĭ
    -0.09
    åĥĸ
    -0.09
    arser
    -0.09
    åĸĦ
    -0.09
    磼
    -0.09
    _each
    -0.09
    æľĢ主è¦ģ
    -0.08
    iors
    -0.08
    æīijåħĭ
    -0.08
    åĭĩ
    -0.08
    POSITIVE LOGITS
    åĪ¸
    0.09
    äºĨåIJ§
    0.09
    éļľ
    0.09
    åįķçĭ¬
    0.09
    巴西
    0.09
    ych
    0.09
     Miche
    0.09
    åºŁè¯Ŀ
    0.08
    è¿ĻçĤ¹
    0.08
    hower
    0.08
    Activations Density 0.008%

    No Known Activations