© 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. 7907
    Prev
    Next
    INDEX
    Explanations

    singleton pregnancy

    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
    zer
    -0.09
    鸳
    -0.08
    ead
    -0.08
    icken
    -0.08
     naked
    -0.08
    owl
    -0.08
    å¯Ĵ
    -0.08
     Aur
    -0.08
     Nas
    -0.07
    æĺİçĻ½
    -0.07
    POSITIVE LOGITS
    çļĦæĦŁæĥħ
    0.10
    ä¹Ŀæ±Ł
    0.10
    é¦Ļæ°´
    0.09
    ä¹ĭæĹħ
    0.09
    æĤ¼
    0.09
    åħĪ天
    0.09
    çļĦé£İéĻ©
    0.09
    æľ¬æĿ¥å°±
    0.09
    /py
    0.09
    éĺ¶æ¢¯
    0.09
    Activations Density 0.130%

    No Known Activations