© 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. 14319
    Prev
    Next
    INDEX
    Explanations

    test-driven development

    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
    elib
    -0.20
    emale
    -0.19
    åıijçĶŁçļĦ
    -0.19
    æ¡ł
    -0.19
    ean
    -0.18
     Fl
    -0.18
    ItemList
    -0.18
    è´Łè½½
    -0.18
    ech
    -0.18
    èľ©
    -0.18
    POSITIVE LOGITS
    è¿Ļ对äºİ
    0.20
     Belgi
    0.19
    isoft
    0.19
    _restore
    0.19
    irs
    0.18
    igned
    0.18
     liqu
    0.18
    漩
    0.18
     Sle
    0.18
    пи
    0.18
    Activations Density 0.020%

    No Known Activations