© 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. 14622
    Prev
    Next
    INDEX
    Explanations

    pdf documents

    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
    ÑĤелем
    -0.20
    oplay
    -0.20
    ä¸Ģç±»
    -0.19
    пÑĢакÑĤик
    -0.19
    .Disclaimer
    -0.19
    ÑĢеги
    -0.19
    ÑĤÑĢади
    -0.19
    elige
    -0.18
    otify
    -0.18
    als
    -0.18
    POSITIVE LOGITS
    pdf
    0.28
    PDF
    0.26
    åħ¨æĸĩ
    0.23
     pdf
    0.23
    论æĸĩ
    0.22
    Pdf
    0.22
     PDF
    0.21
    /pdf
    0.21
     Pdf
    0.21
    读åIJİ
    0.20
    Activations Density 0.038%

    No Known Activations