© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38313
    Prev
    Next
    INDEX
    Explanations

    multi- followed by a word

    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
    ku
    -0.09
    æ¯ıæ¯ı
    -0.09
     hass
    -0.08
    ÙĤسÙħ
    -0.08
    æĹłå½¢
    -0.08
    åĪ°å¤Ħ
    -0.08
    åįģéĩĮ
    -0.08
    ä¸į失
    -0.08
    ä¸Ģ声
    -0.08
    ç¡®
    -0.08
    POSITIVE LOGITS
    èĢĮåıĪ
    0.11
    ollen
    0.10
    éĩįç£ħ
    0.10
    大æ´ĭ
    0.09
     sclerosis
    0.09
    æIJ¦
    0.09
    åħī彩
    0.09
     ÑģебÑı
    0.09
    åĮ»ç§ij
    0.09
    åIJįæł¡
    0.09
    Activations Density 0.027%

    No Known Activations