© 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. 62518
    Prev
    Next
    INDEX
    Explanations

    renal fibrosis, ischemia, diabetes

    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
    ä¸įæĩĤ
    -0.11
    taire
    -0.10
    æ¿Ģ
    -0.09
    失信
    -0.09
    è¯ļå®ŀ
    -0.09
    åIJĿ
    -0.09
    åİ»åģļ
    -0.09
    éĽī
    -0.09
    ä¸įäºĨ解
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    POSITIVE LOGITS
    èĤł
    0.10
    å½Ĵå±ŀ
    0.10
     дог
    0.09
    ви
    0.09
     Sebast
    0.08
    akeup
    0.08
    ä¼ij
    0.08
    é²Ń
    0.08
    ãĥĬãĥ«
    0.08
    arms
    0.08
    Activations Density 0.351%

    No Known Activations