© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15369
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    opal
    -0.24
    åIJĦè¡Į
    -0.20
    å§Ķç»Ħç»ĩ
    -0.20
    å¾Ī好çļĦ
    -0.19
    leigh
    -0.18
    ä¸Ģ份
    -0.18
    åĬ³
    -0.18
    泪
    -0.18
    æĸ°æĪ¿
    -0.18
    лÑİÑĩ
    -0.17
    POSITIVE LOGITS
    èģļçĦ¦
    0.31
     focused
    0.28
     focuses
    0.28
     focusing
    0.27
     focus
    0.27
    æļĤæŶ
    0.23
     specifically
    0.22
    æݢ讨
    0.21
    focused
    0.21
    åĽłä¸ºæĪij
    0.21
    Activations Density 0.379%

    No Known Activations