© 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. 12213
    Prev
    Next
    INDEX
    Explanations

    washing and cleaning

    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
    èIJ¥
    -0.21
    isse
    -0.21
    /lab
    -0.21
    cade
    -0.20
    å®ŀå®ŀåľ¨åľ¨
    -0.19
    glass
    -0.19
    à¦Ľ
    -0.19
     Та
    -0.19
    omb
    -0.19
    æİĺ
    -0.19
    POSITIVE LOGITS
    åijµæĬ¤
    0.23
    å¼Ģå°ģ
    0.23
    ä¸įéĢĤåIJĪ
    0.22
    łéĻ¤
    0.22
    æ¸ħæ´Ĺ
    0.22
    éĿ¢æĸĻ
    0.21
    çıŀ
    0.21
    æĿIJè´¨
    0.20
    pet
    0.20
    è¡£çī©
    0.20
    Activations Density 0.011%

    No Known Activations