© 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. 13375
    Prev
    Next
    INDEX
    Explanations

    award recipients and honorees

    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
    åħ¬åı¸çļĦ
    -0.22
    æ£Ģå¯ŁéĻ¢
    -0.22
    emic
    -0.22
    ç¬Ļ
    -0.21
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.21
    éŀħ
    -0.20
    éŨå¤ĸ
    -0.20
    家ãģ®
    -0.20
    æįŀ
    -0.20
    åŃ¦æł¡çļĦ
    -0.20
    POSITIVE LOGITS
    å¥ĸ
    0.26
    å½ĵå¹´
    0.23
     Award
    0.21
    éģĹ
    0.21
    å½ĵæĹ¥
    0.20
     fellow
    0.20
     award
    0.20
    hook
    0.18
     prize
    0.18
    -NLS
    0.18
    Activations Density 0.029%

    No Known Activations