© 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. 15152
    Prev
    Next
    INDEX
    Explanations

    comma followed by specific words

    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
    âĢ¦↵↵↵↵
    -0.20
    ardo
    -0.19
    ¹Ħ
    -0.18
    ÑĨÑĭ
    -0.18
    ä¹ĭæīĢ
    -0.18
    ники
    -0.18
    åĴĮ社ä¼ļ
    -0.18
    å©ī
    -0.18
    å¯Ĵ
    -0.17
    æŁ¿
    -0.17
    POSITIVE LOGITS
    åIJĦä½į
    0.25
    亲çĪ±çļĦ
    0.24
    èĢģ人家
    0.23
    éĻĽä¸ĭ
    0.23
    ÙħصاÙĦØŃ
    0.22
    إص
    0.21
    çĶ¨æĪ·æıIJä¾Ľ
    0.20
    ÙħصÙĦØŃØ©
    0.20
    èıģ
    0.20
    读èĢħ
    0.20
    Activations Density 0.047%

    No Known Activations