© 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. 13407
    Prev
    Next
    INDEX
    Explanations

    as the name says/suggests

    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
    çĢĽ
    -0.20
    ä¸įåłª
    -0.19
    erno
    -0.19
    Toronto
    -0.19
    athom
    -0.18
    çľĭçľĭ
    -0.18
    åľ¨æĪijçļĦ
    -0.18
    ÑĦон
    -0.17
    RAW
    -0.17
     coch
    -0.17
    POSITIVE LOGITS
    çĤ·
    0.21
    åŃº
    0.21
    verse
    0.20
    å¼ĢéŨ
    0.20
    顾
    0.20
    Localized
    0.19
    ä¸İä¼Ĺ
    0.18
    辫
    0.18
    éĤ£ä¹Īç®Ģåįķ
    0.18
    èĢĮæĿ¥
    0.18
    Activations Density 0.043%

    No Known Activations