© 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. 10741
    Prev
    Next
    INDEX
    Explanations

    locations of places

    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
    instein
    -0.19
     Hund
    -0.19
    åįĥéĩĮ
    -0.19
    åľ¨åħ¨åĽ½
    -0.19
    ä¹ĭåŁİ
    -0.19
    ç«Ļåľ¨
    -0.19
    çĽ²
    -0.19
    纫
    -0.18
    åĽ½éĺ²
    -0.18
    æľī害
    -0.18
    POSITIVE LOGITS
    .rectangle
    0.23
    å²Ļ
    0.20
    欢è¿İ
    0.20
    delegate
    0.19
    åºŃ
    0.19
     delegate
    0.19
    çIJĨæĢ§
    0.19
    Anth
    0.18
    å¹´é¾Ħ段
    0.18
    .delegate
    0.17
    Activations Density 0.076%

    No Known Activations