© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    dates and days

    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
    æŶ任
    -0.10
    åįĪé¤IJ
    -0.09
    æѤåīį
    -0.09
    å±IJ
    -0.09
    æĪIJ绩åįķ
    -0.09
    æıŃ示
    -0.09
     zwy
    -0.09
     defaultManager
    -0.09
    åŁ¤
    -0.09
    ä¸Ĭå¹´
    -0.09
    POSITIVE LOGITS
    è¿Ľåħ¥åĪ°
    0.09
    ops
    0.09
    å°±è¿Ļæł·
    0.09
    鬼
    0.08
    æħ¢æħ¢çļĦ
    0.08
    丰åİļ
    0.08
    å®ŀåľ¨
    0.08
     Locked
    0.08
    åĿ¦
    0.08
    大ä¼Ĺ
    0.08
    Activations Density 0.088%

    No Known Activations