© 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. 7686
    Prev
    Next
    INDEX
    Explanations

    power plant or station

    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
    éģĵåħ·
    -0.11
    èĸª
    -0.09
    arte
    -0.09
    çĹ
    -0.08
    æĪIJéķ¿ä¸º
    -0.08
     Gerr
    -0.08
     giãn
    -0.08
    ún
    -0.08
    ads
    -0.08
     currentItem
    -0.08
    POSITIVE LOGITS
    ç«ĻçĤ¹
    0.10
     пи
    0.10
    åĬłå·¥åİĤ
    0.10
    ç«Ļ
    0.09
    触åıĬ
    0.09
    æ³ħ
    0.09
    åŁºåľ°
    0.09
    æľ¬ç«Ļ
    0.09
    å·«
    0.09
    æĬķèµĦé¢Ŀ
    0.09
    Activations Density 0.061%

    No Known Activations