© 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. 10832
    Prev
    Next
    INDEX
    Explanations

    engine, horsepower, powered by

    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
    -animate
    -0.20
    æŀī
    -0.19
    åŀ¢
    -0.19
    è¤ļ
    -0.19
    éĻį温
    -0.18
     Sheldon
    -0.18
    otomy
    -0.18
    帷
    -0.18
    owie
    -0.17
    ç£IJ
    -0.17
    POSITIVE LOGITS
    åŁ¹
    0.21
    æIJŃéħį
    0.20
    æĸ¹éĿ¢
    0.20
    eno
    0.19
    桧
    0.19
    佶
    0.19
     اÙĦÙĪØŃ
    0.19
     epub
    0.18
    ä¸ĢèĦļ
    0.18
    æĥħåł±
    0.18
    Activations Density 0.030%

    No Known Activations