© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    legal judgments and claims

    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
    æīįæĺ¯
    -0.23
    æĺİ天
    -0.21
    说ä¸įå®ļ
    -0.21
    ä¸ĭåij¨
    -0.20
     lately
    -0.20
    ä¸įèĩ³äºİ
    -0.19
    楷
    -0.19
    ä¸ĭ次
    -0.19
    ä¸ĭä¸Ģ个
    -0.19
    Hopefully
    -0.18
    POSITIVE LOGITS
    éļıåį³
    0.27
    åijĹ
    0.27
    éļıåIJİ
    0.26
    认为
    0.25
    éģĤ
    0.24
    并äºİ
    0.23
    åĹ£
    0.23
    就被
    0.23
    å°±æѤ
    0.21
    åıªå¾Ĺ
    0.21
    Activations Density 0.130%

    No Known Activations