© 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. 51817
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and "api"

    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
    ner
    -0.08
    æĢĿç»´æĸ¹å¼ı
    -0.08
     Bri
    -0.08
    inox
    -0.08
    çİ«çij°
    -0.07
     Territory
    -0.07
    ost
    -0.07
    rove
    -0.07
    nost
    -0.07
    è¢ħ
    -0.07
    POSITIVE LOGITS
    ä¸Ģéģį
    0.10
    ä¸ĢæĬĬ
    0.10
    ä¼łè¯´
    0.10
    ä¹Łæľīä¸ĢäºĽ
    0.10
    æĹłæķĮ
    0.10
    æ¬ł
    0.10
    éªģ
    0.10
    æľīæĦıæĢĿ
    0.10
    abbo
    0.09
    ä¸Ģ个æĺ¯
    0.09
    Activations Density 0.081%

    No Known Activations