© 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. 16689
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    缩
    -0.20
    鸣
    -0.18
     bath
    -0.18
     etiquette
    -0.18
    åħķ
    -0.17
    æķ´é¡¿
    -0.17
     Gerald
    -0.17
    sar
    -0.17
     Abb
    -0.17
    STD
    -0.17
    POSITIVE LOGITS
     kaps
    0.22
    éĻħ
    0.21
    å¥ł
    0.20
    æĪĸå¤ļ
    0.19
    rame
    0.19
    æĺ¯éĿŀ
    0.19
    atcher
    0.19
    éħ¥
    0.19
    vil
    0.19
    æİ°
    0.19
    Activations Density 0.087%

    No Known Activations