© 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. 14170
    Prev
    Next
    INDEX
    Explanations

    physical ailments

    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
    æIJª
    -0.24
    亲åĪĩ
    -0.24
    ounding
    -0.21
    itles
    -0.20
    åĬ«
    -0.20
     redund
    -0.19
    ç«ĭãģ¦
    -0.19
    âīĮ
    -0.19
    åĵģæł¼
    -0.18
    欢
    -0.18
    POSITIVE LOGITS
    积累
    0.23
     ног
    0.21
    æī¿åıĹ
    0.21
    æľ¬èµĽåŃ£
    0.20
    累计
    0.20
    éļIJæĤ£
    0.20
    æĦŁåıĹ
    0.20
    ç®
    0.20
    éĹ®é¢ĺæĺ¯
    0.19
    åı¯æݧ
    0.19
    Activations Density 0.018%

    No Known Activations