© 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. 37894
    Prev
    Next
    INDEX
    Explanations

    religious and institutional terms

    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·¹
    -0.10
    æľīæ¯Ĵ
    -0.10
    .cycle
    -0.09
     Inherits
    -0.09
    åħļåĴĮåĽ½å®¶
    -0.09
    æĭŃ
    -0.09
    é¦ĸè½®
    -0.09
    辨
    -0.09
    ehr
    -0.08
    éħįæĸ¹
    -0.08
    POSITIVE LOGITS
    赦
    0.11
    æĮ½æķij
    0.10
    èĥ½è¾¾åĪ°
    0.10
    ç¥ŀä»Ļ
    0.10
     ÑĢемонÑĤ
    0.09
    erala
    0.09
    ä»Ĺ
    0.09
    æķij人
    0.09
    éŃĶæ³ķ
    0.09
    èįĩ
    0.09
    Activations Density 0.041%

    No Known Activations