© 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. 286
    Prev
    Next
    INDEX
    Explanations

    greatly followed by positive outcomes

    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
    æĢ§å¼º
    -0.29
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.26
    æĽ´å¼º
    -0.25
    wards
    -0.24
    ically
    -0.24
    ities
    -0.24
    å¿ĥè·³
    -0.24
    ä¸Ģç§Ĵ
    -0.24
     chá»Ĺ
    -0.23
    -stop
    -0.23
    POSITIVE LOGITS
     appreciated
    0.25
     influence
    0.23
     influenced
    0.22
    èĬĴ
    0.22
    odon
    0.22
     jun
    0.22
     respects
    0.21
    oose
    0.21
     components
    0.21
     component
    0.21
    Activations Density 0.056%

    No Known Activations