© 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. 11158
    Prev
    Next
    INDEX
    Explanations

    epidural anesthesia

    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
     заÑĢ
    -0.22
    åķIJ
    -0.19
    onis
    -0.19
    羣
    -0.18
    enumer
    -0.18
    verbatim
    -0.18
    æµ·è¾¹
    -0.18
    sut
    -0.18
     embar
    -0.17
    çħ²
    -0.17
    POSITIVE LOGITS
    æĿī
    0.21
    æ¸ħåįİ
    0.20
    _configuration
    0.19
    chem
    0.18
    éĽªèĬ±
    0.18
    shaft
    0.18
    æĭĽçīĮ
    0.18
    Combined
    0.18
    åľ¨åĽ½åĨħ
    0.17
    _tok
    0.17
    Activations Density 0.005%

    No Known Activations