© 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. 20637
    Prev
    Next
    INDEX
    Explanations

    for someone or something

    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
    æĭ¨
    -0.09
    æ±Ŀ
    -0.09
    inis
    -0.08
    åłĨ
    -0.08
    éģ®
    -0.08
    建åįİ
    -0.08
     веÑī
    -0.08
     RULE
    -0.08
    ربÙĬ
    -0.07
    зем
    -0.07
    POSITIVE LOGITS
    éĥijéĩį
    0.10
    主管éĥ¨éŨ
    0.10
    åıĪ好
    0.09
    åħļå·¥å§Ķ
    0.09
    主åĬŀæĸ¹
    0.09
    ToBounds
    0.09
    åĵŃäºĨ
    0.09
     Schiff
    0.09
    .nc
    0.09
     Spicer
    0.09
    Activations Density 0.039%

    No Known Activations