© 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. 51724
    Prev
    Next
    INDEX
    Explanations

    data presented, obtained, or indicate

    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
    åŁİå¸Ĥ建设
    -0.10
    çľĭäºĨä¸Ģçľ¼
    -0.10
    注æĺİæĿ¥æºIJ
    -0.09
    两ä½į
    -0.09
    çļĦçľ¼åħī
    -0.09
    æ·ĭ
    -0.08
    çĸĹæ³ķ
    -0.08
    çĦī
    -0.08
     peaked
    -0.08
    å³°
    -0.08
    POSITIVE LOGITS
    èµĦæĸĻ
    0.10
    åĪĢ
    0.10
     obtained
    0.10
    ç»ıéªĮåĢ¼
    0.09
    æľįä»İ
    0.09
    à°¬
    0.09
    /results
    0.09
    éªł
    0.09
     results
    0.09
    åĩºèĩª
    0.09
    Activations Density 0.467%

    No Known Activations