© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61956
    Prev
    Next
    INDEX
    Explanations

    abuse of power and monopoly

    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
    æģ¯
    -0.10
    éĻª
    -0.09
    ä¾
    -0.09
    硬
    -0.09
     ê¶
    -0.09
    éĤĻ
    -0.09
    é¢Ŀ
    -0.09
    _ctxt
    -0.09
    ocus
    -0.08
     fine
    -0.08
    POSITIVE LOGITS
     monopoly
    0.11
    èĤ©è´Ł
    0.11
    è¦ģ害
    0.10
    èł¹
    0.10
     entrusted
    0.10
    æİĮæı¡
    0.10
    åŀĦæĸŃ
    0.09
    åķ¬
    0.09
    æİĮæı¡äºĨ
    0.09
    æĿijéķĩ
    0.09
    Activations Density 0.037%

    No Known Activations