© 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. 11658
    Prev
    Next
    INDEX
    Explanations

    Americans with Disabilities Act (ADA)

    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
    aries
    -0.20
    è¾ĵç»Ļ
    -0.19
    ëĤľ
    -0.17
    idor
    -0.17
    ulario
    -0.17
    亲çĪ±çļĦ
    -0.17
    ä»ĵä½į
    -0.17
    åľĥ
    -0.17
    æIJ¬åĪ°
    -0.17
    çīĿ
    -0.17
    POSITIVE LOGITS
    çĮ´
    0.19
    çīĻ
    0.18
    åįĵ
    0.17
    conc
    0.17
     Lov
    0.17
    anto
    0.17
     Awakening
    0.17
     Disabilities
    0.17
    åįĥéĩĮ
    0.17
    -disabled
    0.16
    Activations Density 0.005%

    No Known Activations