© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    shortage, prices, inventory, scarcity

    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
    绽
    -0.24
    æĶ¶åĪ°äºĨ
    -0.21
    èĭĮ
    -0.20
    å¹³åĿ¦
    -0.20
    顺çķħ
    -0.19
    èIJ
    -0.19
    褪
    -0.19
    æķŀ
    -0.19
    "math
    -0.19
    ило
    -0.18
    POSITIVE LOGITS
    ç¨Ģ缺
    0.34
    é«ĺä»·
    0.29
    ä»·æł¼ä¸Ĭ涨
    0.29
     scarcity
    0.26
    çŁŃ缺
    0.24
    紧缺
    0.24
    å¤ĩçĶ¨
    0.23
    æĦĪ
    0.22
    è¡¥åģ¿
    0.22
    æĺĤè´µ
    0.22
    Activations Density 0.179%

    No Known Activations