© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7499
    Prev
    Next
    INDEX
    Explanations

    delivery mode and pregnancy type

    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
    Hur
    -0.09
    涸
    -0.09
     Taste
    -0.09
    å»ĵ
    -0.09
    åĸĦ
    -0.09
     Lunch
    -0.09
    èµ·æĿ¥
    -0.09
    æ½®
    -0.09
     tide
    -0.09
     Hur
    -0.09
    POSITIVE LOGITS
    åīª
    0.10
    çł´è£Ĥ
    0.09
    è·ĥ
    0.09
    ç¾Ĭ
    0.09
    è§ģè¯ģäºĨ
    0.08
    人æĢ§åĮĸ
    0.08
     scissors
    0.08
    èĭŀ
    0.08
    emme
    0.08
    èįī
    0.08
    Activations Density 0.261%

    No Known Activations