© 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. 13173
    Prev
    Next
    INDEX
    Explanations

    submitted by or found in

    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
    åįĩèµ·
    -0.20
    ILD
    -0.20
    _ENABLED
    -0.19
     Darren
    -0.19
    oden
    -0.18
     NOTES
    -0.18
    .LayoutParams
    -0.17
    åĪ¤
    -0.17
    æķŀ
    -0.17
    sen
    -0.17
    POSITIVE LOGITS
    大家åı¯ä»¥
    0.21
    对æѤ
    0.20
    ä¸ĢåIJ¬
    0.19
    害
    0.19
     Lau
    0.19
    æ°ijæĹıæĸĩåĮĸ
    0.18
    éĥ½æ²¡æľī
    0.18
    ãĤ¿ãĤ¤
    0.18
    è¿Ļ两天
    0.18
    æĹħ游å±Ģ
    0.18
    Activations Density 0.002%

    No Known Activations