© 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. 16536
    Prev
    Next
    INDEX
    Explanations

    grade II building

    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
    ipes
    -0.22
    amus
    -0.20
     seri
    -0.19
    >Loading
    -0.19
    à¹Ħ
    -0.18
    å¤ĦåĪĨ
    -0.18
    éĢ¢
    -0.18
    æĸ°æĪ¿
    -0.18
     paradigm
    -0.17
    URY
    -0.17
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.24
    ä¸ĢéĹª
    0.22
    åģļä¸Ģ个
    0.21
    伪
    0.20
    åIJį为
    0.20
    ä¸Ģ个å°ı
    0.20
    ä¸ĢæĬ¹
    0.20
    ä¼ı
    0.19
    çĶ¨äºº
    0.19
    åģĩ
    0.19
    Activations Density 0.355%

    No Known Activations