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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8484
    Prev
    Next
    INDEX
    Explanations

    services and findings

    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
    ury
    -0.10
    ä¸įçķĻ
    -0.09
    åĪ®
    -0.09
    URY
    -0.09
    大æ´ĭ
    -0.08
    æĺ¯éĿŀ
    -0.08
    å¼ĢéĺĶ
    -0.08
    æĸĹ
    -0.08
    icken
    -0.08
    窥
    -0.08
    POSITIVE LOGITS
    好çļĦ
    0.14
    æľīäºĨ
    0.11
    èī¯å¥½çļĦ
    0.11
     ÑħоÑĢоÑĪ
    0.11
    è¿ĩ硬
    0.10
    ç²¾æ¹Ľ
    0.10
    ä¼ĺèī¯
    0.10
    nemonic
    0.10
    ETO
    0.10
    æīįåįİ
    0.10
    Activations Density 0.097%

    No Known Activations