© 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. 9085
    Prev
    Next
    INDEX
    Explanations

    capability of generating

    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¯æĥ³èĢĮçŁ¥
    -0.09
    æĺ¥å¤ı
    -0.09
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.09
    以åħ¶
    -0.09
    涵
    -0.08
    å±ķå¼Ģ
    -0.08
    éĵºè®¾
    -0.08
    åĬłåħ¥äºĨ
    -0.08
    ä¸ĢäºĮ
    -0.08
    æı©
    -0.08
    POSITIVE LOGITS
    å®ĥåı¯ä»¥
    0.10
    æŀľçĦ¶
    0.10
     apparently
    0.09
    è²Įä¼¼
    0.09
    åį³ä½¿æĺ¯
    0.09
    ä¿Ł
    0.09
    åįķä¸Ģ
    0.09
    æŀľ
    0.09
    åį³ä½¿
    0.08
    æĺ¯å¤ļä¹Ī
    0.08
    Activations Density 0.145%

    No Known Activations