© 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. 16680
    Prev
    Next
    INDEX
    Explanations

    yards in sports

    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°ıéķĩ
    -0.19
    NEY
    -0.19
    æīĢåľ¨
    -0.18
    æĤ¨çļĦåŃ©åŃIJ
    -0.18
    çķ´
    -0.18
     Gn
    -0.18
    éĩĮçļĦ
    -0.18
    åĽ°
    -0.17
    oria
    -0.17
    ence
    -0.17
    POSITIVE LOGITS
    è¾ĥéķ¿
    0.22
    å¾Īéķ¿
    0.19
    ä¸Ģ举
    0.19
    èĪĴå¿ĥ
    0.19
    llu
    0.18
    使çĶ¨ç¶²è·¯
    0.18
    è¡ĮåĬ¨è®¡åĪĴ
    0.18
    ç»ĦåĽ¾
    0.18
    çķĻè¨ĢæĿ¿
    0.18
    åĢĴåľ¨
    0.18
    Activations Density 0.001%

    No Known Activations