© 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. 8486
    Prev
    Next
    INDEX
    Explanations

    largely on or at

    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
     ÐľÐ¸
    -0.10
    éĻŁ
    -0.10
    äºĨå¤ļå°ij
    -0.10
    -Cs
    -0.09
    äºĨä¸Ģ
    -0.09
    äºĨå¾Īå¤ļ
    -0.09
    -heading
    -0.09
    大家éĥ½
    -0.08
    çĶĺ
    -0.08
    룬
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸Ģ件
    0.11
    æĺ¯ä¸Ģ座
    0.10
    eno
    0.09
    åħ³äºİæĪij们
    0.09
    è´´å¿ĥ
    0.09
    æĺ¯ä¸Ģ项
    0.09
    è´¿
    0.09
    ç«ŀ
    0.08
    atically
    0.08
    å§
    0.08
    Activations Density 0.124%

    No Known Activations