© 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. 52889
    Prev
    Next
    INDEX
    Explanations

    political resistance

    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
    æķ¦
    -0.10
    èĸª
    -0.09
    ä¸į解
    -0.09
    åħļé£İ
    -0.09
    æİ¥åĪ°
    -0.09
    otomy
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    åħ¢
    -0.09
    èħIJ
    -0.09
    æĶ¾å¼Ģ
    -0.09
    POSITIVE LOGITS
    声
    0.10
    论è¯ģ
    0.09
    åĩĿèģļ
    0.09
    hits
    0.09
    éĺ»åĬĽ
    0.09
    寸
    0.09
     scraps
    0.08
    éĤ£ä¸ªäºº
    0.08
    Toolkit
    0.08
    辩论
    0.08
    Activations Density 0.133%

    No Known Activations