© 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. 19374
    Prev
    Next
    INDEX
    Explanations

    Nu and variations followed by words

    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
    æīĵæī®
    -0.09
    azo
    -0.09
    naire
    -0.09
    modifiers
    -0.08
     fer
    -0.08
     vicinity
    -0.08
    vern
    -0.08
    iosis
    -0.08
    笼
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    POSITIVE LOGITS
    åĴĮè°IJ
    0.09
    ë¡Ń
    0.09
     trần
    0.09
    clé
    0.09
    eli
    0.09
    æľĿ
    0.09
    HEST
    0.08
    ovo
    0.08
    å´¤
    0.08
    /new
    0.08
    Activations Density 0.019%

    No Known Activations