© 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. 51478
    Prev
    Next
    INDEX
    Explanations

    celiac disease

    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
    å¨ĺ
    -0.09
    çŁ¢
    -0.09
    éķ¿å¤§
    -0.09
    æĹĥ
    -0.08
    æĻºåķĨ
    -0.08
    _less
    -0.08
    åı£æ°Ķ
    -0.08
    éĻ¢éķ¿
    -0.08
    横
    -0.08
    ä¼ī
    -0.08
    POSITIVE LOGITS
    è¿«ä¸įåıĬå¾ħ
    0.09
    éŨæĪ·
    0.09
    æĢ¥éľĢ
    0.09
    _ma
    0.09
    æ´§
    0.08
    裾
    0.08
    otor
    0.08
    .entrySet
    0.08
     miejs
    0.08
    å´¤
    0.08
    Activations Density 0.219%

    No Known Activations