© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11050
    Prev
    Next
    INDEX
    Explanations

    scientific and technical study terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ç²¾åĩĨ
    -0.41
    å®ĺ宣
    -0.39
    æĸĩæĹħ
    -0.38
    管æݧ
    -0.37
     emoji
    -0.37
     emojis
    -0.37
    èµĭèĥ½
    -0.37
     hashtag
    -0.36
    ç½ij红
    -0.36
    ä¸Ģ带ä¸Ģè·¯
    -0.35
    POSITIVE LOGITS
     AIDS
    0.38
     daÃŁ
    0.37
     videot
    0.32
    ä¼łçľŁ
    0.29
    Č↵
    0.28
    .sourceforge
    0.28
    	StringBuffer
    0.28
    计ç®Ĺæľº
    0.28
     StringBuffer
    0.27
     modem
    0.27
    Activations Density 6.092%

    No Known Activations