© 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. 26927
    Prev
    Next
    INDEX
    Explanations

    citations and medical terms

    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
    igin
    -0.09
    eing
    -0.09
    å¼ĢäºĨ
    -0.09
    满满
    -0.09
     apparently
    -0.09
    oler
    -0.08
    沿线
    -0.08
    ṡ
    -0.08
    shi
    -0.08
    è¿IJæ²³
    -0.08
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.11
    常è§ģçļĦ
    0.10
    æĸ¯é¡¿
    0.09
    ä¸ŃæľĢ
    0.09
    åIJĪçIJĨçļĦ
    0.09
    æľĢ常è§ģçļĦ
    0.09
    ä¸ĢèĪ¬
    0.08
    æĶ¹éĿ©åıijå±ķ
    0.08
    ä¸ĢèĪ¬çļĦ
    0.08
     ìĿ¼ë°ĺ
    0.08
    Activations Density 0.500%

    No Known Activations