© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    concludes or conclusion

    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
    çīµ
    -0.21
    éĹ®é¢ĺæĺ¯
    -0.20
    æ´»
    -0.20
    æĶ¯
    -0.20
    ä¸Ģ次æĢ§
    -0.19
    åªĸ
    -0.19
    åı°
    -0.18
    دÙĨ
    -0.18
    å©į
    -0.18
    åĪĨæŀIJå¸Ī
    -0.18
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.26
    以ä¸Ĭ
    0.26
    æĢ»èĢĮè¨Ģä¹ĭ
    0.24
     Conclusion
    0.22
     concludes
    0.22
    åĪ°è¿ĻéĩĮ
    0.22
     laat
    0.21
    ttl
    0.21
    tá
    0.21
    Conclusion
    0.20
    Activations Density 0.004%

    No Known Activations