© 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. 51398
    Prev
    Next
    INDEX
    Explanations

    year and followed by a capitalized word

    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
    红楼
    -0.12
    ä»Ĭãģ¯
    -0.12
    ä»ĬåĽŀãģ¯
    -0.12
    çİ°åľ¨å¾Īå¤ļ
    -0.12
    æľ¬æ¬¡æ´»åĬ¨
    -0.12
    çİ°åľ¨å·²ç»ı
    -0.11
    ä½Ĩ她
    -0.11
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.11
    ä»Ĭ天å°ıç¼ĸ
    -0.11
    æľ¬åľºæ¯ĶèµĽ
    -0.11
    POSITIVE LOGITS
    çĶ±äºİ
    0.09
    æĪijæĬĬ
    0.09
    beg
    0.08
    éĢĤ
    0.08
    æĬĬ
    0.08
    éĴĪ对
    0.08
    ä¸ĢäºĽ
    0.08
     inve
    0.07
    inherits
    0.07
    west
    0.07
    Activations Density 0.095%

    No Known Activations