© 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. 6474
    Prev
    Next
    INDEX
    Explanations

    thickening or concentrated liquid

    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
    osa
    -0.09
    楼ä¸ĭ
    -0.08
    WORD
    -0.08
    ç½¹
    -0.08
    æŀģ大çļĦ
    -0.08
    èѬ
    -0.08
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.08
    æŀģåħ¶
    -0.08
    æļĸ
    -0.08
    .CV
    -0.08
    POSITIVE LOGITS
    ä¸ĢåľĪ
    0.09
    ãģĤãĤĮ
    0.09
    ë³´
    0.09
    IfNeeded
    0.09
    SELF
    0.08
    itu
    0.08
    ä¸ĢçĤ¹
    0.08
    è±Į
    0.08
     TH
    0.08
    å·´å·´
    0.08
    Activations Density 0.006%

    No Known Activations