© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12422
    Prev
    Next
    INDEX
    Explanations

    producer, writer, actor, musician

    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
    åIJĦèĩª
    -0.20
    éĨį
    -0.18
    ä¸Ģ个个
    -0.17
    稼
    -0.17
    读åIJİæĦŁ
    -0.17
     üzerinden
    -0.17
    noc
    -0.17
    !!!
    -0.17
     hart
    -0.17
    çļĦåīįæıIJä¸ĭ
    -0.17
    POSITIVE LOGITS
    综åIJĪæĢ§
    0.21
    积累äºĨ
    0.21
    èĩªåĪ¶
    0.20
    pora
    0.19
    å¤ļ项
    0.19
    ç³Ĭ
    0.19
    社群
    0.19
     cú
    0.19
    åħ¨æĸ¹ä½į
    0.19
    çĪª
    0.18
    Activations Density 0.088%

    No Known Activations