© 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. 15235
    Prev
    Next
    INDEX
    Explanations

    biblical passages or references

    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
    Ǧ
    -0.22
    ç£ķ
    -0.20
    ocols
    -0.20
    诨
    -0.19
    éŃij
    -0.19
    âĬĭ
    -0.19
    èĥ´
    -0.19
    âĩı
    -0.19
    èĢĹ
    -0.19
    ÇŃ
    -0.18
    POSITIVE LOGITS
    æııè¿°
    0.24
    æĸĩ
    0.23
    è¯Ń
    0.23
    ç¯ĩç«ł
    0.23
    åIJİ代
    0.23
    ç»ĩ
    0.22
    æıIJåĪ°
    0.22
    iore
    0.22
    åİŁæĸĩ
    0.22
    è¨Ģ
    0.21
    Activations Density 0.039%

    No Known Activations