© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 355
    Prev
    Next
    INDEX
    Explanations

    in part or portions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    /dist
    -0.25
     lia
    -0.24
    å±ķæľĽ
    -0.24
    ãģ®ãģ¯
    -0.23
    ä»Ģä¹Īåij¢
    -0.23
     namely
    -0.23
    embre
    -0.21
    eve
    -0.21
    hua
    -0.21
    _FIX
    -0.21
    POSITIVE LOGITS
    è¶ħåĩº
    0.30
    ä¾µçĬ¯
    0.24
    æĬĦè¢Ń
    0.23
     Matter
    0.23
    è¶ħè¿ĩ
    0.23
    åĩºä¼Ĺ
    0.22
     any
    0.22
    ä¸įå°ijäºİ
    0.21
    æĪ¢
    0.21
    ç²¾åįİ
    0.21
    Activations Density 0.011%

    No Known Activations