© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31442
    Prev
    Next
    INDEX
    Explanations

    elements of labor, pain, delivery

    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
    EEE
    -0.09
    对å¤ĸ
    -0.09
    бо
    -0.08
     susp
    -0.08
    ø
    -0.08
    å³»
    -0.08
    Ùģت
    -0.08
    å¼Ģåĩº
    -0.08
    ç»´ä¿®
    -0.08
    çİ°
    -0.08
    POSITIVE LOGITS
    åĨ¥
    0.09
    产åĮº
    0.09
    è¾Ľèĭ¦
    0.09
    ä¸Ģè·¯ä¸Ĭ
    0.09
    信念
    0.09
    panion
    0.09
    åĮĸçļĦ
    0.09
    åĸľæĤ¦
    0.09
    æĢµ
    0.09
    äºīè®®
    0.08
    Activations Density 0.135%

    No Known Activations