© 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. 16528
    Prev
    Next
    INDEX
    Explanations

    mdb, mdf, .asp/.aspx files

    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
    erce
    -0.22
    ushman
    -0.21
    ockey
    -0.19
    icken
    -0.19
    åı°ä¸Ĭ
    -0.19
    è¿ĻæĶ¯
    -0.18
     iNdEx
    -0.18
    PropertyParams
    -0.18
     Dut
    -0.18
     Rut
    -0.18
    POSITIVE LOGITS
    æĸĩ件
    0.46
     file
    0.40
     files
    0.40
    ãĥķãĤ¡ãĤ¤ãĥ«
    0.40
     íĮĮìĿ¼
    0.34
     ÑĦайл
    0.32
     æĸĩ件
    0.32
     ÑĦайла
    0.30
    -file
    0.30
    file
    0.28
    Activations Density 0.281%

    No Known Activations