© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    | verb | that/the/both

    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
    æĪijå½ĵæŶ
    -0.13
    åģļè¿ĩ
    -0.12
    æĺ¨å¤©
    -0.10
     каÑĤал
    -0.10
    说è¿ĩ
    -0.10
    éĤ£æ¬¡
    -0.10
     yesterday
    -0.10
    ç½ij讯
    -0.10
     бÑĭло
    -0.10
    ä¼ļ使
    -0.10
    POSITIVE LOGITS
    æѤæŶ
    0.10
     dut
    0.09
    ç»Īäºİ
    0.09
    ä¸įæĪIJ
    0.09
    ä¼łæĿ¥
    0.09
    注æĦıåĪ°
    0.08
     оÑģÑĤа
    0.08
     оказÑĭва
    0.08
    SCAN
    0.08
    éĢģæĿ¥
    0.08
    Activations Density 0.222%

    No Known Activations