© 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. 15875
    Prev
    Next
    INDEX
    Explanations

    charity and community work

    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
    åij³
    -0.24
    æĿĥå¨ģ
    -0.19
    BuilderFactory
    -0.19
    çĹĩ
    -0.18
     requestOptions
    -0.18
    sl
    -0.18
    åIJ¹
    -0.18
     cấu
    -0.18
     пÑĢава
    -0.18
    è¿Ļåĩłä¸ª
    -0.17
    POSITIVE LOGITS
    åħ¬çĽĬæ´»åĬ¨
    0.29
    åĽŀé¦Ī
    0.28
    åħ¬çĽĬ
    0.25
    表彰
    0.23
    ourg
    0.22
    äºĭä¸ļ
    0.22
    æģ¤
    0.22
    åħ³çĪ±
    0.21
    æħĪåĸĦ
    0.20
    æĦŁåĬ¨
    0.20
    Activations Density 0.047%

    No Known Activations