© 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. 15639
    Prev
    Next
    INDEX
    Explanations

    greenery, plants, and landscaping

    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
     ÑģÑĤÑĢаÑħ
    -0.21
    èĪ
    -0.20
    æĸ¹åľĨ
    -0.19
    æľĢéķ¿
    -0.19
    æĬ¤èº«ç¬¦
    -0.18
     camps
    -0.18
    æĸ§
    -0.18
    _verbose
    -0.18
    -wide
    -0.18
    Axes
    -0.18
    POSITIVE LOGITS
    çݯç»ķ
    0.28
    ery
    0.24
    翳
    0.24
    åĽ´ç»ķ
    0.22
    åľ¨è¿ĩ渡
    0.21
    ä¸Ģæłĭ
    0.20
    è¦ĨçĽĸçİĩ
    0.20
    -filled
    0.20
    amental
    0.19
    两岸
    0.19
    Activations Density 0.019%

    No Known Activations