© 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. 50515
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    eland
    -0.10
    .alibaba
    -0.09
    ä¸ĢäºĽ
    -0.09
    ìĩĦ
    -0.09
    æľĢå¤ļ
    -0.09
    /english
    -0.09
    ä¸Ģéĥ¨åĪĨ
    -0.09
    .nlm
    -0.09
    çijķ
    -0.09
    ROTO
    -0.09
    POSITIVE LOGITS
    æĮģä¹ħ
    0.12
    æľīä»»ä½ķ
    0.12
    ä»»ä½ķå½¢å¼ı
    0.11
    ä»»ä½ķæŶåĢĻ
    0.11
    èĨº
    0.10
    æĮģç»Ń
    0.10
    è¿Łè¿Ł
    0.09
     any
    0.09
     or
    0.09
    太ä¹ħ
    0.09
    Activations Density 0.050%

    No Known Activations