© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15714
    Prev
    Next
    INDEX
    Explanations

    has been + past participle

    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
    æ¯ıä¸Ģ个人
    -0.20
    åıĪèĥ½
    -0.20
    td
    -0.19
    æĹ©æĹ¥
    -0.19
    ty
    -0.18
    ä¸ĭ次
    -0.18
     adulthood
    -0.18
     idi
    -0.18
    å¦Ĥæŀľæĺ¯
    -0.18
    éģ¥è¿ľ
    -0.17
    POSITIVE LOGITS
    以ä¾Ĩ
    0.23
    以æĿ¥
    0.23
    åŁ¹åħ»åѦçĶŁ
    0.20
    ãģļãģ£ãģ¨
    0.19
    ä¸Ģ缴éĥ½
    0.18
    ipse
    0.18
    çĽijæµĭ
    0.18
    поÑĤ
    0.18
    RAL
    0.18
    ä¸įä½ı
    0.18
    Activations Density 0.071%

    No Known Activations