© 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. 51912
    Prev
    Next
    INDEX
    Explanations

    verbs following 'he'

    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
    åĴĮ个人
    -0.09
    åĪ¶
    -0.08
    ETER
    -0.08
    åĪĨæĺİ
    -0.08
    é¼İ
    -0.08
    iens
    -0.08
    è¡·å¿ĥ
    -0.08
    leases
    -0.08
     gotta
    -0.08
    alic
    -0.08
    POSITIVE LOGITS
    以便
    0.11
    çĦ¶åIJİåĨį
    0.10
    缴åĪ°
    0.10
    为客æĪ·
    0.10
    åıªæĺ¯ä¸ºäºĨ
    0.10
    汶å·Ŀ
    0.09
    åıªä¸º
    0.09
    æĥħå½¢
    0.09
    æŃ¤ä¸¾
    0.09
     заÑĤем
    0.09
    Activations Density 0.154%

    No Known Activations