© 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. 42
    Prev
    Next
    INDEX
    Explanations

    future events or plans

    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¬èº«å°±
    -0.27
    åIJĥäºı
    -0.26
    æľ¬èº«å°±æĺ¯
    -0.26
    æĭĴç»Ŀ
    -0.25
    丢äºĨ
    -0.25
    -loving
    -0.24
    ä»İæĿ¥æ²¡æľī
    -0.24
     unintended
    -0.24
     unintention
    -0.24
     dispro
    -0.23
    POSITIVE LOGITS
     sooner
    0.38
    åIJİç»Ń
    0.36
    å°½æĹ©
    0.35
     soon
    0.34
    éļıåIJİ
    0.33
     ÑģкоÑĢо
    0.33
    尽快
    0.32
    å±ĬæŶ
    0.32
    ä¸įä¹ħ
    0.32
     thereafter
    0.31
    Activations Density 0.039%

    No Known Activations