© 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. 362
    Prev
    Next
    INDEX
    Explanations

    holidays and celebrations

    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
     push
    -0.23
    åıijå¸ĥä¼ļ
    -0.23
    ?("
    -0.22
    ĥģ
    -0.22
    åħ¬å¯ĵ
    -0.22
    éļıæŶ
    -0.21
    çĹħæĪ¿
    -0.21
    ä¸ĢæŃ¥æŃ¥
    -0.21
    	push
    -0.21
     transaction
    -0.21
    POSITIVE LOGITS
     fireworks
    0.37
     rockets
    0.32
     patriot
    0.30
     patriotism
    0.29
    çĦ°
    0.29
     gunfire
    0.29
     Patriot
    0.28
    çĥŁçģ«
    0.28
    çĥŁèĬ±
    0.28
    ç¾İåĽ½äºº
    0.28
    Activations Density 0.006%

    No Known Activations