© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and course

    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
    anos
    -0.10
    /live
    -0.09
    æĵĺ
    -0.09
    好çİ©
    -0.09
    æĹłç¼Ŀ
    -0.09
    è¹ļ
    -0.09
    åĽ½ç½ij
    -0.09
    å´ĩ
    -0.09
    ones
    -0.09
    æ½ľæ°´
    -0.09
    POSITIVE LOGITS
     Franz
    0.09
    èĢIJå¿ĥ
    0.09
     Pace
    0.09
    æħ¢æħ¢çļĦ
    0.09
     вÑĢемени
    0.09
    æŶéĹ´
    0.09
    éĢŁåº¦
    0.08
     пÑĢоÑĩ
    0.08
    è¿Ľåº¦
    0.08
    åľŁè±Ĩ
    0.08
    Activations Density 0.031%

    No Known Activations