© 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. 21219
    Prev
    Next
    INDEX
    Explanations

    man who

    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
    åı¯æĥľ
    -0.09
     scr
    -0.08
    æľį
    -0.08
    çĶ²
    -0.08
    æĺİçıł
    -0.08
    åįĵ
    -0.08
     jud
    -0.08
    Specifier
    -0.07
     either
    -0.07
    å¿į
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Ī
    0.10
     huyết
    0.10
    çļĦçĶŁåij½
    0.09
    éĤ£ä¹Īå¤ļ
    0.09
    å¤Ħå¤Ħ
    0.09
     ÐľÐ¾Ñģков
    0.09
    ä¸ĢçĽ´ä»¥æĿ¥
    0.09
    骨æŀ¶
    0.09
     ÑĩаÑģÑĤо
    0.09
    å¹ħ
    0.09
    Activations Density 0.049%

    No Known Activations