© 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. 15373
    Prev
    Next
    INDEX
    Explanations

    alternative or substitute

    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
    å²Ń
    -0.24
    pora
    -0.20
     Mob
    -0.20
    idan
    -0.19
    羨
    -0.19
    ç»´
    -0.19
    æľĢå¤ļ
    -0.19
    .removeAll
    -0.19
    oni
    -0.18
    oeff
    -0.18
    POSITIVE LOGITS
    æĽ¿ä»£
    0.48
    ä»£æĽ¿
    0.40
     alternatives
    0.39
     Altern
    0.35
     alternative
    0.32
    Altern
    0.29
     substitutes
    0.29
    æĽ¿è¡¥
    0.29
     Alternative
    0.28
    æľīæĽ´å¥½çļĦ
    0.28
    Activations Density 0.296%

    No Known Activations