© 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. 15604
    Prev
    Next
    INDEX
    Explanations

    later / eventually / future-oriented

    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
    è¶Ĭæĺ¯
    -0.21
    é«ĺæĸ°
    -0.20
    çļĦåIJĮæŶ
    -0.20
    posted
    -0.19
     поддеÑĢжива
    -0.19
    ?><
    -0.19
    _bottom
    -0.17
    çī§åľº
    -0.17
     trending
    -0.17
     backed
    -0.17
    POSITIVE LOGITS
     later
    0.71
    åIJİæĿ¥
    0.70
    later
    0.67
     Later
    0.56
    å¾Įä¾Ĩ
    0.56
    Later
    0.56
     später
    0.54
    æĹ¥åIJİ
    0.42
    æѤåIJİ
    0.39
     eventually
    0.38
    Activations Density 0.192%

    No Known Activations