© 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. 13723
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    istan
    -0.21
    åĭĺ
    -0.21
    prech
    -0.19
    elong
    -0.19
    ista
    -0.19
    weg
    -0.19
    主ä¹ī
    -0.18
    èĢħ
    -0.18
    ika
    -0.18
    æĸĩåŃĹ
    -0.18
    POSITIVE LOGITS
    (es
    0.21
    é¦Ĩ
    0.20
    éļ¾è¿ĩ
    0.18
    館
    0.18
    (s
    0.17
    -gallery
    0.17
    brew
    0.17
    åºĶæĢ¥é¢Ħæ¡Ī
    0.17
    梯éĺŁ
    0.17
    éĴĬ
    0.17
    Activations Density 0.058%

    No Known Activations