© 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. 15313
    Prev
    Next
    INDEX
    Explanations

    judgments or perceptions

    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
    å§ĭäºİ
    -0.27
    æĪijä¸Ģ缴
    -0.21
    æ³·
    -0.21
    paging
    -0.19
    æł·çļĦ
    -0.19
    æĪij说
    -0.19
    说çļĦæĺ¯
    -0.19
    æĸ°æł¼å±Ģ
    -0.18
    åĩ¡æĺ¯
    -0.18
    æł·
    -0.18
    POSITIVE LOGITS
    认为
    0.23
    æĪĸèĢħ
    0.21
    æĪĸèĢħæĺ¯
    0.20
    åĪ¤æĸŃ
    0.20
    ãģĤãĤĭãģĦãģ¯
    0.19
    æĢĢçĸij
    0.19
    大éĿ¢ç§¯
    0.19
    ijľ
    0.19
    èªįçĤº
    0.19
     hoặc
    0.18
    Activations Density 0.070%

    No Known Activations