© 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. 51916
    Prev
    Next
    INDEX
    Explanations

    emotional distress and tears

    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
    idle
    -0.10
    راب
    -0.09
    ounc
    -0.09
    åħļåĨħ
    -0.08
    åŁİ
    -0.08
    æĬĹè®®
    -0.08
    对人ä½ĵ
    -0.08
    Sanders
    -0.08
    è£ģ
    -0.08
    æĽ³
    -0.08
    POSITIVE LOGITS
    æĦŁåĬ¨
    0.17
    泪
    0.16
    泪水
    0.15
    潸
    0.15
    çľ¼æ³ª
    0.15
    æ·ļ
    0.14
     tears
    0.14
     Tears
    0.14
    æĥħæĦŁ
    0.13
    æµģ泪
    0.13
    Activations Density 0.035%

    No Known Activations