© 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. 52186
    Prev
    Next
    INDEX
    Explanations

    investigated and analyzed

    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
    ä¸İåħ¶ä»ĸ
    -0.10
    ç»ĻåĪ«äºº
    -0.09
    èģĮ称
    -0.09
    åIJĦèĩªçļĦ
    -0.09
    æºī
    -0.09
    oux
    -0.09
    åĩºæĿ¥äºĨ
    -0.08
    主é¢ĺæ´»åĬ¨
    -0.08
     Earl
    -0.08
    à§İ
    -0.08
    POSITIVE LOGITS
    æł·æľ¬
    0.09
     samples
    0.09
    éĮĦ
    0.09
    è°ĥæŁ¥
    0.09
    è¯ķ
    0.09
     tested
    0.09
    ego
    0.09
     sample
    0.09
    èĢĥå¯Ł
    0.08
     Nh
    0.08
    Activations Density 0.125%

    No Known Activations