© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    leader or leading something

    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
    лоÑģÑĮ
    -0.10
    eo
    -0.09
    åķ¬
    -0.08
    窨
    -0.08
    eil
    -0.08
     Hook
    -0.08
    ctime
    -0.08
    寮
    -0.08
     hooked
    -0.08
    .wp
    -0.08
    POSITIVE LOGITS
    ä¸ĸçķĮä¸Ĭ
    0.12
    öz
    0.09
    æĬ¥ç¤¾
    0.09
    éĻIJé¢Ŀ
    0.09
    åıĹçĽĬ
    0.09
    æķ¢
    0.09
    çģ¾åĮº
    0.08
    год
    0.08
    éĢŀ
    0.08
    itud
    0.08
    Activations Density 0.010%

    No Known Activations