© 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. 37158
    Prev
    Next
    INDEX
    Explanations

    master of sports or title holder

    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
    ç¼µ
    -0.10
    åĴĮ个人
    -0.09
    åıĭ好
    -0.09
    å¸ĪçĶŁ
    -0.09
    æľĭåıĭ们
    -0.09
    .foundation
    -0.08
    äºĨå¤ļå°ij
    -0.08
    å¤ļå°ij
    -0.08
    åIJĦçķĮ
    -0.08
    engers
    -0.08
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.16
    级
    0.14
    级åĪ«
    0.14
    ä¸Ģ级
    0.12
    称åı·
    0.12
    -level
    0.11
    çŃī级
    0.10
     level
    0.10
    ä¸ī级
    0.10
    ç´ļ
    0.10
    Activations Density 0.085%

    No Known Activations