© 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. 16674
    Prev
    Next
    INDEX
    Explanations

    dimension, land, area, world, country

    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
    å¹³æŶ
    -0.27
    éĶĩ
    -0.24
     every
    -0.24
    éĶİ
    -0.23
    éĶķ
    -0.23
    éķħ
    -0.23
    éķ±
    -0.23
    æ¦į
    -0.23
     arts
    -0.22
    éķİ
    -0.22
    POSITIVE LOGITS
    主åĬĽ
    0.31
    åīįæľŁ
    0.29
    æ½ľåľ¨
    0.28
    æ½ľåĬĽ
    0.28
    æݢ索
    0.27
    åĪĿæŃ¥
    0.27
    æľīä¿¡å¿ĥ
    0.26
    ðŁĺ¦
    0.26
    æľīæľĽ
    0.26
    åĭĺæİ¢
    0.25
    Activations Density 0.019%

    No Known Activations