© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36718
    Prev
    Next
    INDEX
    Explanations

    excerpt from

    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
    å¤ļæł·
    -0.09
    KeyName
    -0.09
     Ùħجرد
    -0.08
    åĿļå®Ī
    -0.08
    ç´¢èµĶ
    -0.08
    çļĦéĤ£ä¸Ģ
    -0.08
    edly
    -0.08
    åħ³åı£
    -0.08
    æ²½
    -0.08
    æ¯ĹéĤ»
    -0.08
    POSITIVE LOGITS
    å°º
    0.10
    ä¸Ģ段
    0.09
    åħīçħ§
    0.09
    åĨĴ
    0.08
    说æĺİ书
    0.08
    æ´»çĿĢ
    0.08
    æĪĸå¤ļ
    0.08
    åľ°åĽ¾
    0.08
    ç͵åύ
    0.08
    lug
    0.08
    Activations Density 0.068%

    No Known Activations