© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15103
    Prev
    Next
    INDEX
    Explanations

    trying to achieve or understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    毫ä¸įçĬ¹è±«
    -0.23
    çļĦåĪ°æĿ¥
    -0.22
    没æľīæĥ³åĪ°
    -0.21
    å¾Īéķ¿
    -0.20
    éĨĴæĿ¥
    -0.20
    æľīæľºä¼ļ
    -0.19
    ä¸Ģå®ļç¨ĭ度
    -0.19
    æľīæŶåĢĻ
    -0.18
    wahl
    -0.18
    åĪ°æĿ¥
    -0.18
    POSITIVE LOGITS
    æijĨèĦ±
    0.23
    平衡
    0.21
    满足
    0.20
     desperately
    0.20
    æ±Ĥ
    0.20
    ç»´æĬ¤
    0.20
     balance
    0.20
    imonial
    0.19
    æĮ¯åħ´
    0.19
    éĺ»æŃ¢
    0.19
    Activations Density 0.096%

    No Known Activations