© 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. 18625
    Prev
    Next
    INDEX
    Explanations

    infection and infected

    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
    èĭ±çī¹
    -0.09
    è°ª
    -0.09
    NEWS
    -0.09
    ãĤ·ãĥª
    -0.09
    ç»·
    -0.09
    apo
    -0.08
    .mainloop
    -0.08
     mij
    -0.08
    è¹ģ
    -0.08
     üzerinden
    -0.08
    POSITIVE LOGITS
    æĦŁæŁĵ
    0.12
     infections
    0.12
     infection
    0.11
    ä¸Ŀä¸Ŀ
    0.09
    æĹºçĽĽ
    0.08
    ä½ľä¸ļ
    0.08
    è®Ń
    0.08
    ä»Ŀ
    0.08
    å¦Ĩ
    0.08
    éĽĢ
    0.08
    Activations Density 0.112%

    No Known Activations