© 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. 7974
    Prev
    Next
    INDEX
    Explanations

    NYC Photographer, teetotal, big fan, firm believer, school prefect, moral relativist, knowledgeable, happy kid, single-issue

    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
    éħĿéħ¿
    -0.10
    åIJĮäºĭ们
    -0.09
    å¸Ĥåľºè§Ħ模
    -0.09
    è¯ķæİ¢
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    ä¸Ģ次
    -0.08
     librarian
    -0.08
    igor
    -0.08
    åĽłåľ°åĪ¶å®ľ
    -0.08
    çļĦ巨大
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģåijĺ
    0.14
    主ä¹īèĢħ
    0.13
    verse
    0.12
     ÑģбоÑĢ
    0.10
     ÑĥÑĩаÑģÑĤник
    0.10
    åıĤä¸İèĢħ
    0.09
    æľīèĥ½åĬĽ
    0.09
    åħļåĴĮåĽ½å®¶
    0.09
    å·¥ä½ľèĢħ
    0.09
     WindowManager
    0.09
    Activations Density 0.318%

    No Known Activations