© 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. 14624
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     ÑĢазнÑĭÑħ
    -0.20
    rets
    -0.18
    gram
    -0.18
    åī©
    -0.18
    ä¸įåIJĮçļĦ
    -0.18
    mlin
    -0.18
    æĸľ
    -0.18
    деÑĤ
    -0.17
    çļĦçŁ¥è¯Ĩ
    -0.17
    åī©ä½Ļ
    -0.17
    POSITIVE LOGITS
    è¿·
    0.22
    è¯ķè¡Į
    0.21
    纨
    0.21
    æĵ¦æĭŃ
    0.20
    山路
    0.20
    Ãły
    0.19
    没æľī太大
    0.19
    æĦļ
    0.19
    æĬķæłĩ
    0.18
    çĪ±ä½ł
    0.18
    Activations Density 0.015%

    No Known Activations