© 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. 9207
    Prev
    Next
    INDEX
    Explanations

    medical complications

    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
    åĵģåij³
    -0.10
    è´ª
    -0.09
    allas
    -0.09
    çĥŃçĪ±
    -0.09
     Duc
    -0.08
     Patt
    -0.08
    ä¹łæĥ¯
    -0.08
    å¤ķéĺ³
    -0.08
    essage
    -0.08
     wise
    -0.08
    POSITIVE LOGITS
    并åıijçĹĩ
    0.20
     complications
    0.15
    itage
    0.12
    åIJİæŀľ
    0.12
     complication
    0.11
    èµ·ãģĵ
    0.09
    å²ļ
    0.09
    鸵
    0.09
    ELS
    0.09
    ä¸Ģç«Ļ
    0.09
    Activations Density 0.374%

    No Known Activations