© 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. 21976
    Prev
    Next
    INDEX
    Explanations

    diabetes, hypertension, insulin resistance

    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
    èļ
    -0.10
    ENE
    -0.09
    æĭ³å¤´
    -0.09
    éłĵ
    -0.08
    éĶ»
    -0.08
     Winds
    -0.08
     @(
    -0.08
    é¡¿
    -0.08
    çľ·
    -0.08
    æ¯ĹéĤ»
    -0.08
    POSITIVE LOGITS
    ç²¾çģµ
    0.10
    èĸĦ
    0.10
     ÑĢазвива
    0.09
    ç§įç§į
    0.09
     ê°ģì¢ħ
    0.09
    æĭĶ
    0.09
    unter
    0.09
    å»īæĶ¿
    0.08
    许å¤ļ
    0.08
    ukan
    0.08
    Activations Density 0.203%

    No Known Activations