© 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. 20402
    Prev
    Next
    INDEX
    Explanations

    draft related terms

    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
    交
    -0.11
    æĸ°æł¼å±Ģ
    -0.10
    饵
    -0.09
    åIJĦ个æĸ¹éĿ¢
    -0.09
    åı«
    -0.09
    çĮ¿
    -0.09
    æĢ»åħ¬åı¸
    -0.09
    resa
    -0.09
    åĿł
    -0.09
    æĢ¥éľĢ
    -0.08
    POSITIVE LOGITS
     drafts
    0.17
     draft
    0.17
    draft
    0.16
    èįīæ¡Ī
    0.15
     Draft
    0.15
    稿
    0.15
    _draft
    0.15
    Draft
    0.14
     drafting
    0.12
     drafted
    0.12
    Activations Density 0.047%

    No Known Activations