© 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. 36523
    Prev
    Next
    INDEX
    Explanations

    de- prefix verbs

    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
    ä¸įèĤ¯
    -0.11
    firm
    -0.10
    娥
    -0.10
    ĺ
    -0.09
    kinson
    -0.09
    æĹłæ¯Ķ
    -0.09
    ä¸ŀ
    -0.09
    oop
    -0.09
    iples
    -0.09
    edef
    -0.09
    POSITIVE LOGITS
     khá»ıi
    0.10
    ÑģÑı
    0.10
    erb
    0.09
    æİīäºĨ
    0.09
    gee
    0.08
    é£ĺ
    0.08
    ending
    0.08
     تÙħاÙħا
    0.08
    PED
    0.08
    zon
    0.08
    Activations Density 0.145%

    No Known Activations