© 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. 8305
    Prev
    Next
    INDEX
    Explanations

    currency denominations

    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
    å²IJ
    -0.09
    æѧ
    -0.09
    akh
    -0.09
    fol
    -0.09
    èĻļ空
    -0.09
    æİĤ
    -0.08
    ÐIJÐŀ
    -0.08
    èħ¹
    -0.08
    жд
    -0.08
    AFP
    -0.08
    POSITIVE LOGITS
    median
    0.09
    .wp
    0.09
    èĪ¬
    0.08
    ä¸ĩåħĥ以ä¸Ĭ
    0.08
    éĶ´
    0.08
    åĢĴæĺ¯
    0.08
    ä¸ĭ游
    0.08
    é»İæĺİ
    0.08
    åĩłå®¶
    0.08
    abet
    0.08
    Activations Density 0.052%

    No Known Activations