© 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. 204
    Prev
    Next
    INDEX
    Explanations

    love triangle, story, two, China, generations

    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
    åºķæ°Ķ
    -0.32
    ä¸ĬéŨ
    -0.28
     politely
    -0.28
    åIJĵ
    -0.28
    æľīæķĪ
    -0.26
    夸大
    -0.25
    ä¸įåĩĨ
    -0.25
    没éĹ®é¢ĺ
    -0.25
    _delegate
    -0.25
    arium
    -0.25
    POSITIVE LOGITS
     generations
    0.40
     intertwined
    0.39
    åıĺè¿ģ
    0.39
    çļĦåij½è¿IJ
    0.38
     births
    0.37
    æķħäºĭ
    0.37
    åij½è¿IJ
    0.36
    ç»ĪçĶŁ
    0.35
     intertw
    0.35
    çļĦæķħäºĭ
    0.35
    Activations Density 0.060%

    No Known Activations