© 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. 63677
    Prev
    Next
    INDEX
    Explanations

    thromboembolism prevention

    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
    馥
    -0.09
    èħ»
    -0.09
    åģļ强
    -0.09
    ä½İä¸ĭ
    -0.09
    éĢĢ
    -0.09
     Anc
    -0.09
    æ½¼
    -0.08
     наÑĢÑĥÑĪен
    -0.08
    dued
    -0.08
    强åĪ¶
    -0.08
    POSITIVE LOGITS
    æĿĤçī©
    0.10
    åĽ½ä¼ģ
    0.09
    èĦī
    0.09
    å¼ĤæĢ§
    0.08
    æ·¤
    0.08
    èĦĪ
    0.08
    å¡ij
    0.08
    é£İéĻ©
    0.08
    psc
    0.08
    ÑģÑĤан
    0.08
    Activations Density 0.189%

    No Known Activations