© 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. 15511
    Prev
    Next
    INDEX
    Explanations

    for [noun]

    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
    ness
    -0.23
    enn
    -0.20
    way
    -0.19
    ä¸įåĪĨ
    -0.19
    bble
    -0.19
     enough
    -0.18
     aggrav
    -0.18
    ifier
    -0.18
    ision
    -0.18
     Maduro
    -0.18
    POSITIVE LOGITS
    æľĪ份
    0.22
    æѤæ¡Ī
    0.20
    æľīå¾Ī大çļĦ
    0.20
     данного
    0.20
    该æ¡Ī
    0.20
    åIJĦ个
    0.20
     каждого
    0.19
    å¾Ī满æĦı
    0.19
    å®ļäºĨ
    0.19
    è¿Ļ个游æĪı
    0.19
    Activations Density 0.231%

    No Known Activations