© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    men, women, or small

    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
    æĪij家
    -0.11
    /tmp
    -0.08
    asca
    -0.08
     Scre
    -0.08
    ãģľ
    -0.08
    robe
    -0.08
    åĿIJçĿĢ
    -0.08
    梯éĺŁ
    -0.08
    å°ģéĿ¢
    -0.07
    ç´§å¯Ĩ
    -0.07
    POSITIVE LOGITS
    çݰ代社ä¼ļ
    0.10
    åIJĮèĥŀ
    0.10
    women
    0.09
    主èIJ¥
    0.09
    èµ°è¿ĩ
    0.09
    ãĢħ
    0.09
    常çĶ¨çļĦ
    0.09
    æĭĻ
    0.09
    é«ĺçŃīéĻ¢æł¡
    0.09
    éĢį
    0.09
    Activations Density 0.030%

    No Known Activations