© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    staff, members, writers, editors

    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
    oration
    -0.22
    kü
    -0.20
    è¡Į人
    -0.20
    utto
    -0.19
     Witnesses
    -0.19
     witnesses
    -0.19
    å¥Ķ
    -0.19
    صاÙĦ
    -0.19
    缮çĿ¹
    -0.19
    人们
    -0.19
    POSITIVE LOGITS
    åĽ¢éĺŁ
    0.26
     team
    0.24
    æĹ¥å¸¸å·¥ä½ľ
    0.23
    åIJĦèĩª
    0.23
    请大家
    0.22
    åľĺéļĬ
    0.22
    æĪĺéĺŁ
    0.21
    ç»Ħéķ¿
    0.21
    åĺ¿
    0.21
    è½®æµģ
    0.21
    Activations Density 0.080%

    No Known Activations