© 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. 18444
    Prev
    Next
    INDEX
    Explanations

    EC classification numbers and enzymes

    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
    åİŁæĿ¥æĺ¯
    -0.10
    é«ĺæ½®
    -0.09
    è¿Ļå¼ł
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    å¡Į
    -0.09
    æ¶Ī
    -0.08
    ä¸ĩéĩĮ
    -0.08
    antis
    -0.08
    ago
    -0.08
    agenda
    -0.08
    POSITIVE LOGITS
    åºŀ
    0.12
    ä¸ĢéĶ®
    0.09
    åĮĸåѦ
    0.09
    Unnamed
    0.08
     chemistry
    0.08
     Kn
    0.08
    æIJª
    0.08
    Fallback
    0.08
     Hands
    0.08
    è°ĥåij³
    0.08
    Activations Density 0.148%

    No Known Activations