© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12215
    Prev
    Next
    INDEX
    Explanations

    commands or phrases

    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
     responseBody
    -0.20
    styleType
    -0.20
    .onreadystatechange
    -0.20
     Kraft
    -0.20
     iNdEx
    -0.20
    actionDate
    -0.20
    ape
    -0.19
     commenter
    -0.19
    Profiler
    -0.19
    .dateFormat
    -0.19
    POSITIVE LOGITS
    èĢĥä¸Ĭ
    0.24
     sẵ
    0.24
     nghè
    0.23
    æĻļé¥Ń
    0.23
    éĢĽè¡Ĺ
    0.23
    åľ¨åľ°ä¸Ĭ
    0.23
    доб
    0.23
    éĺŁåijĺ
    0.23
    æĺİçĻ½äºĨ
    0.23
    åĬĽæ°Ķ
    0.23
    Activations Density 0.042%

    No Known Activations