© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    phase of

    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
    æĹ¥æĬ¥
    -0.20
    ofs
    -0.18
    ä¸Ģè§Ī
    -0.17
    pedia
    -0.17
    è¿Ļ两ç§į
    -0.17
    راÙĤ
    -0.17
     ÑĢазнÑĭÑħ
    -0.16
    åŃIJéĩĮ
    -0.16
    äºĮåŃĹ
    -0.16
    åIJĮä¸Ģ
    -0.16
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.22
    æ¡ĮéĿ¢
    0.22
    ä¹Łå°±æĺ¯
    0.21
    èĬ±å¼Ģ
    0.20
    rollers
    0.19
    æĪijä»¬åľ¨
    0.19
    æļ¨
    0.18
    пÑĥÑģ
    0.18
    äººæł¼
    0.18
    彧
    0.18
    Activations Density 0.048%

    No Known Activations