© 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. 9271
    Prev
    Next
    INDEX
    Explanations

    negative abstract concepts

    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
    æĬĵ
    -0.09
    å¾Īå¤ļæľĭåıĭ
    -0.09
    pios
    -0.08
    è¦ģåģļ好
    -0.08
    å¾Īå¤ļ人
    -0.08
    ÑĪÑĥ
    -0.08
     ë§İìĿ´
    -0.08
    ohan
    -0.08
    éĻ¤äºĨ
    -0.08
    quete
    -0.08
    POSITIVE LOGITS
    åŀĴ
    0.09
    å¯Ŀ室
    0.09
    念头
    0.09
    çijĻ
    0.08
    å²ļ
    0.08
    弧
    0.08
    ä»ħ代表
    0.08
    çķĻä¸ĭæĿ¥
    0.08
    å¼ĵ
    0.08
    çļĦèĦ¸
    0.08
    Activations Density 0.240%

    No Known Activations