© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    license to practice law

    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
    åħ´èµ·
    -0.29
    åħħå®ŀ
    -0.23
    解æŀIJ
    -0.23
    ä½ĵåĬĽ
    -0.22
    åĮºåĨħ
    -0.20
    Bindable
    -0.19
    Ven
    -0.19
    常说
    -0.19
    notEmpty
    -0.18
    æĶ¾å¤§
    -0.18
    POSITIVE LOGITS
     ÐŁÐ¾Ñĩем
    0.24
     ÐIJлекÑģан
    0.23
     кнопк
    0.23
    utex
    0.22
    åĬ£
    0.20
     заÑĢегиÑģÑĤ
    0.20
    _ComCallableWrapper
    0.20
    èµĪ
    0.19
    æľīä»»ä½ķ
    0.19
    èµĦæł¼
    0.19
    Activations Density 0.069%

    No Known Activations