© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    on patrol, personal use, rental income, related activities

    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
     spiral
    -0.23
    çĶļ
    -0.21
    æĪIJåĬŁ
    -0.20
    çĭłæĬĵ
    -0.19
    åľĪ
    -0.19
     Jade
    -0.19
    å¤į
    -0.19
    æ®Ĭ
    -0.19
     ép
    -0.19
    夺å¾Ĺ
    -0.19
    POSITIVE LOGITS
    æ´»åĬ¨ä¸Ń
    0.31
    æ´»åĬ¨
    0.28
     деÑıÑĤелÑĮноÑģÑĤи
    0.26
     activities
    0.23
    æ´»åĭķ
    0.23
    ãĤ¿ãĤ¤ãĥŁ
    0.22
    èģĮè´£
    0.21
    ç»ıèIJ¥æ´»åĬ¨
    0.21
    åįķèģĮä¸ļ
    0.21
    åĪĪ
    0.21
    Activations Density 0.044%

    No Known Activations