© 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. 38322
    Prev
    Next
    INDEX
    Explanations

    corporate tyranny, wealth, control, governance, leader

    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
    æ°´æĻ¶
    -0.10
     ׼׾׾
    -0.09
    åİŁèijĹ
    -0.09
    idge
    -0.09
    burn
    -0.09
    åıĮè¾¹
    -0.09
    è¡Įä¸ļåıijå±ķ
    -0.09
    æ¸ħ代
    -0.09
    äºĭä¸ļåıijå±ķ
    -0.09
    vale
    -0.09
    POSITIVE LOGITS
    /company
    0.10
    åĴĮ个人
    0.09
    éĹ´
    0.09
    巨头
    0.09
    andr
    0.09
    ç»ıèIJ¥èĢħ
    0.08
    eur
    0.08
    à®ļ
    0.08
    éĹ´çļĦ
    0.08
    ized
    0.08
    Activations Density 0.011%

    No Known Activations