© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1436
    Prev
    Next
    INDEX
    Explanations

    focus and distractions

    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
    æľ¨è´¨
    -0.27
    ä¸į认è¯Ĩ
    -0.25
     Mim
    -0.24
    æĹłåģ¿
    -0.24
    大èĥĨ
    -0.23
    模仿
    -0.23
    bir
    -0.23
    æĭ¥æĬ±
    -0.23
    建æĪIJåIJİ
    -0.22
    æīįçŁ¥éģĵ
    -0.22
    POSITIVE LOGITS
     distracted
    0.36
    è®®é¢ĺ
    0.36
     distractions
    0.36
    focus
    0.35
    çĦ¦çĤ¹
    0.35
    åħ³æ³¨
    0.35
     focus
    0.33
     foc
    0.33
     priorities
    0.33
     overshadow
    0.32
    Activations Density 0.113%

    No Known Activations