© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    adverbs before adjectives or nouns

    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
    亶
    -0.09
    éĵĽ
    -0.09
    èħĭ
    -0.09
    assage
    -0.09
    ç¬ijç¬ij
    -0.08
    ç§ijæĬĢèĤ¡ä»½
    -0.08
    驯
    -0.08
    åĩĦ
    -0.08
    æľ¬èº«
    -0.08
    é£ĺ
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.11
    æīĵçĿĢ
    0.10
    åĮĹæĸ¹
    0.10
    æĸ¹éĿ¢
    0.10
    abinet
    0.09
    ÐĽÐĺ
    0.09
    弩
    0.09
    éĿŀ常å¤ļçļĦ
    0.09
    å°±å¾Ĺ
    0.09
     gob
    0.08
    Activations Density 0.081%

    No Known Activations