© 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. 15049
    Prev
    Next
    INDEX
    Explanations

    radical extremism and Islam

    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
    è°ĥçIJĨ
    -0.23
    æĥ¬æĦı
    -0.19
    å¹¿æ³Ľåħ³æ³¨
    -0.19
    éĮĦ
    -0.19
    æīª
    -0.18
    éħIJ
    -0.18
    åĽ¢åľĨ
    -0.18
     Wer
    -0.17
    æĢĿç´¢
    -0.17
    çİ©èĢį
    -0.17
    POSITIVE LOGITS
    åģı
    0.20
     zeal
    0.20
    æļ´åĬĽ
    0.20
    .dtd
    0.19
     extreme
    0.19
    ovan
    0.19
    roid
    0.18
    kins
    0.18
    们
    0.18
    lickr
    0.18
    Activations Density 0.014%

    No Known Activations