© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    tiny or small

    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
    年以ä¸Ĭ
    -0.23
    æĥ°
    -0.19
    apis
    -0.18
    çű
    -0.18
    æŃ£å¸¸ä½¿çĶ¨
    -0.18
    é³Ŀ
    -0.18
    åķ¸
    -0.18
    åıªèĥ½è¯´
    -0.17
    -ignore
    -0.17
    å±Ĥ次
    -0.17
    POSITIVE LOGITS
    /small
    0.37
    /tiny
    0.35
     (\<
    0.31
     tiny
    0.28
     (<
    0.27
    çļĦå°ı
    0.26
    tiny
    0.26
    å°ı
    0.26
    å¾Īå°ı
    0.26
    ä¸ĢçĤ¹
    0.24
    Activations Density 0.201%

    No Known Activations