© 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. 52015
    Prev
    Next
    INDEX
    Explanations

    always followed by a verb

    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
    MLE
    -0.09
    ç»ĪçĶŁ
    -0.09
    éªij士
    -0.09
    ç»Ŀ
    -0.09
    ewan
    -0.09
    лем
    -0.09
    解æĶ¾
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.08
    ä¹İ
    -0.08
    ä¸ĸä¿Ĺ
    -0.08
    POSITIVE LOGITS
    åĬŀäºĭ
    0.11
    berger
    0.09
    è§īå¾Ĺå¾Ī
    0.09
    gard
    0.09
    è§īå¾Ĺ
    0.09
    大夫
    0.09
    åIJ¬åĪ°
    0.09
    åħ¥æīĭ
    0.09
    以为
    0.09
    注æĦıåĪ°
    0.09
    Activations Density 0.024%

    No Known Activations