© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    station names and lines

    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
    æĭĶ
    -0.21
    èij¬
    -0.21
     pet
    -0.19
    大éĿ¢ç§¯
    -0.19
    ä¸Ńå¤ĸ
    -0.19
    形象
    -0.18
    æ»ŀ
    -0.18
     fern
    -0.18
    æĬĵä½ı
    -0.18
    çĻ»
    -0.18
    POSITIVE LOGITS
    çļĦè·¯ä¸Ĭ
    0.38
    éĢĶä¸Ń
    0.37
    éģĵè·¯ä¸Ĭ
    0.31
    çļĦéģĵè·¯
    0.30
    è·¯ä¸Ĭ
    0.29
    çļĦæĸ¹åIJij
    0.28
    éĢĶ
    0.28
    è¿ĻæĿ¡è·¯
    0.28
    çĽ´è¾¾
    0.27
    è·¯ç¨ĭ
    0.27
    Activations Density 0.297%

    No Known Activations