© 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. 14459
    Prev
    Next
    INDEX
    Explanations

    flaws and deficiencies

    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¢ŀåĢ¼æľįåĬ¡
    -0.23
    éĩįè¦ģæĦıä¹ī
    -0.21
    æĸ°ä¸ī
    -0.20
    è¿Ļç§įäºĭæĥħ
    -0.19
    好å¤Ħ
    -0.19
    è¿Ļæł·çļĦè¯Ŀ
    -0.19
    å¤ļç§įå½¢å¼ı
    -0.19
    inters
    -0.19
    åħ´è¶£
    -0.18
     гол
    -0.18
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.28
    缺éĻ·
    0.27
    åľ¨äºİ
    0.27
    çİ°è¡Į
    0.25
     flaw
    0.23
     flaws
    0.23
    ä¸į足
    0.23
    çŁŃæĿ¿
    0.23
    åŃĺåľ¨äºİ
    0.23
    æīĢåľ¨
    0.22
    Activations Density 0.083%

    No Known Activations