© 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. 51861
    Prev
    Next
    INDEX
    Explanations

    acting awards and nominations

    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
    æªĦ
    -0.10
    该åİ¿
    -0.09
    ç¼ļ
    -0.08
    æľºåĪ¶
    -0.08
    å§Ĭ妹
    -0.08
     slab
    -0.08
    çļĦä¸Ģåijĺ
    -0.08
     Steven
    -0.08
    欤
    -0.08
    æĦĪ
    -0.08
    POSITIVE LOGITS
    ooth
    0.09
    åĢ¾
    0.09
    çĭ
    0.08
    ики
    0.08
    Portable
    0.08
    asty
    0.08
    å«£
    0.08
    ฯ
    0.08
    æĻ®æĥł
    0.08
     Portable
    0.08
    Activations Density 0.029%

    No Known Activations