© 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. 397
    Prev
    Next
    INDEX
    Explanations

    questions starting with "why do"

    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
     coursework
    -0.24
     whats
    -0.24
    aid
    -0.24
    ä»Ģä¹ĪæĦıæĢĿ
    -0.23
    oc
    -0.23
    .documentation
    -0.21
     Haram
    -0.21
    Äĥn
    -0.21
    obot
    -0.21
    ideas
    -0.21
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.28
    æľīäºĽäºº
    0.27
    곡
    0.27
    è¿Ļä¹Īå¤ļ
    0.27
    人们
    0.26
    æľīçļĦ人
    0.26
    ording
    0.23
    çľĭä¸įåĪ°
    0.23
    ä¸įæĸŃåľ°
    0.23
    ITTER
    0.23
    Activations Density 0.045%

    No Known Activations