© 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. 16242
    Prev
    Next
    INDEX
    Explanations

    pay and book online

    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
    prm
    -0.19
    ValuePair
    -0.19
     Utilities
    -0.19
    åIJĦèĩª
    -0.19
    èij«
    -0.18
    aisy
    -0.18
    åĪĽ
    -0.17
    anding
    -0.17
    èķĻ
    -0.17
    egade
    -0.17
    POSITIVE LOGITS
     âĵĺ
    0.20
     TripAdvisor
    0.19
    inyin
    0.19
    å½ĵä»ĸ
    0.18
    åİ»çľĭçľĭ
    0.18
    ä¸į满æĦı
    0.18
    éķĩ
    0.18
    imately
    0.18
     av
    0.17
    Trust
    0.17
    Activations Density 0.093%

    No Known Activations