© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20105
    Prev
    Next
    INDEX
    Explanations

    business functions and operations

    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
    ngle
    -0.10
    Gear
    -0.09
    èŀĥèŁ¹
    -0.09
    è®©æĽ´å¤ļ
    -0.09
    èŁ¹
    -0.08
    åĴĮ个人
    -0.08
    æ´¼
    -0.08
    ç§ģ人
    -0.08
    èĩ³ä»Ĭ
    -0.08
    ä¸įåIJĮç¨ĭ度
    -0.08
    POSITIVE LOGITS
    顾客
    0.10
    çĽĸ
    0.10
    å¾Ĺ天
    0.09
    çݳ
    0.09
    entai
    0.09
    ä¼Ľ
    0.09
    anders
    0.09
     ürün
    0.09
     внеÑĪ
    0.09
    å¯ĨåĪĩ缸åħ³
    0.08
    Activations Density 0.223%

    No Known Activations