© 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. 16932
    Prev
    Next
    INDEX
    Explanations

    scientific models and calculations

    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
    åĸŁ
    -0.21
     measuring
    -0.20
    atty
    -0.20
    erot
    -0.20
    èĪIJ
    -0.20
    isclosed
    -0.19
     кÑĢÑĥ
    -0.19
    趸
    -0.18
    زÙĦ
    -0.18
    agg
    -0.18
    POSITIVE LOGITS
    模åŀĭ
    0.28
     predictions
    0.28
     models
    0.27
    é¢Ħæµĭ
    0.26
    模æĭŁ
    0.24
    models
    0.24
    ters
    0.23
     predicts
    0.23
    é¢Ħè¨Ģ
    0.23
     model
    0.23
    Activations Density 0.163%

    No Known Activations