© 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. 58460
    Prev
    Next
    INDEX
    Explanations

    domains and email addresses

    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
    çµ·
    -0.10
    æļĿ
    -0.10
    æĻļå¹´
    -0.10
    æĶ¯éĺŁ
    -0.10
    åĨ·ç¬ij
    -0.09
    åģļ梦
    -0.09
    lü
    -0.08
    åĬŀ好
    -0.08
    读æĩĤ
    -0.08
     Karn
    -0.08
    POSITIVE LOGITS
    .com
    0.14
    .net
    0.13
    ç½ij
    0.10
    .org
    0.10
    .info
    0.09
    ä¸įä¸Ĭ
    0.09
    -online
    0.09
    .co
    0.09
    .NET
    0.08
    .me
    0.08
    Activations Density 0.143%

    No Known Activations