© 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. 18697
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    à¹Ģà¸Ńà¸ĩ
    -0.09
    æĪı
    -0.09
    athe
    -0.09
    è¯ķè¡Į
    -0.08
    åĽŀ头
    -0.08
    åıĤèĤ¡
    -0.08
    ä¹Ĵ
    -0.08
    ButtonTitles
    -0.08
    称ä¹ĭ
    -0.08
    微信åı·
    -0.08
    POSITIVE LOGITS
    仪
    0.11
    eron
    0.09
    mpl
    0.08
    eam
    0.08
    objectId
    0.08
    kn
    0.08
    åĬłå¤§
    0.08
     ìĿĺìĤ¬
    0.08
    çĹĩ
    0.08
    è¿Ļ两ç§į
    0.08
    Activations Density 0.110%

    No Known Activations