© 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. 2688
    Prev
    Next
    INDEX
    Explanations

    bronchial remodelling, body weight, cell carcinoma

    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
    èĪģ
    -0.10
    å¥ī
    -0.10
    ä¸įä¸ĭ
    -0.10
    è°Ĵ
    -0.09
    祺
    -0.09
     Madagascar
    -0.09
    å½ĵ天
    -0.08
    帮
    -0.08
    ä¸įå®Į
    -0.08
    ENCY
    -0.08
    POSITIVE LOGITS
    夷
    0.09
    éĵ°
    0.08
    æıª
    0.08
    æĥ¨
    0.08
    è¿Ļä¸Ģ次
    0.08
    å°ıå¾®
    0.08
    ç¾ģ
    0.08
    ÃŁe
    0.08
     Bom
    0.08
    ä¾Ŀ
    0.08
    Activations Density 0.464%

    No Known Activations