© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20850
    Prev
    Next
    INDEX
    Explanations

    quinoline derivatives

    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
    hil
    -0.10
    èĦ±èIJ½
    -0.08
     háºŃu
    -0.08
     cá»Ń
    -0.08
     strat
    -0.08
    ishi
    -0.08
    éĻ¶
    -0.08
    åĪĩæĸŃ
    -0.08
    æķĪçİĩ
    -0.08
    è±ģ
    -0.08
    POSITIVE LOGITS
    å¤įæ´»
    0.10
    igne
    0.10
     LoggerFactory
    0.09
    nova
    0.09
    olesterol
    0.09
    åĩ¹
    0.09
     Pun
    0.09
    ipse
    0.09
    è®©æĽ´å¤ļ
    0.09
    èķĪ
    0.09
    Activations Density 0.314%

    No Known Activations