© 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. 44
    Prev
    Next
    INDEX
    Explanations

    saving and investing

    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
     liberties
    -0.28
    ç»ħ
    -0.28
    éĢļåijĬ
    -0.28
    ä¾µçĬ¯
    -0.27
    åı¬åĽŀ
    -0.26
    æĭĺçķĻ
    -0.26
    åĵķ
    -0.26
    æĿĢ人
    -0.26
    解æķ£
    -0.25
    åºĶæĢ¥é¢Ħæ¡Ī
    -0.25
    POSITIVE LOGITS
     investing
    0.38
    æĬķåħ¥
    0.32
     invested
    0.31
     investment
    0.30
     Investing
    0.30
    积èĵĦ
    0.30
    åĤ¨èĵĦ
    0.29
     инвеÑģÑĤи
    0.29
    æ¯ıæľĪ
    0.29
    èµ·æŃ¥
    0.28
    Activations Density 0.014%

    No Known Activations