© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18576
    Prev
    Next
    INDEX
    Explanations

    DNS servers and domain names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.10
    æ·³
    -0.10
    irie
    -0.10
    æĭĩæĮĩ
    -0.09
    å°¼æĸ¯
    -0.09
    å¦ĥ
    -0.09
    ÙĪÙī
    -0.09
    æīī
    -0.09
    æĹĮ
    -0.09
    multipart
    -0.09
    POSITIVE LOGITS
     DNS
    0.09
    byname
    0.08
     sue
    0.08
    lá
    0.08
    ãĥĬãĤ¤
    0.08
    åIJ¬è¯Ŀ
    0.08
    elor
    0.08
     завиÑģим
    0.08
    letes
    0.08
    aret
    0.08
    Activations Density 0.065%

    No Known Activations