© 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. 51507
    Prev
    Next
    INDEX
    Explanations

    surprise or unexpected events and outcomes

    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
    æ½ĩ
    -0.10
    çªĪ
    -0.08
     Imper
    -0.08
    äºij
    -0.08
    å¾ģæ±Ĥ
    -0.08
    scar
    -0.08
    éĺĨ
    -0.08
    ingo
    -0.08
    mour
    -0.07
    æµģä¼ł
    -0.07
    POSITIVE LOGITS
    æĥĬåĸľ
    0.23
     surprises
    0.18
     surprise
    0.17
    æĥĬ讶
    0.13
    é©ļ
    0.13
     surprised
    0.13
    æĦıå¤ĸ
    0.13
     surpr
    0.13
     Surprise
    0.12
    æĥĬå¥ĩ
    0.12
    Activations Density 0.016%

    No Known Activations