© 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. 10791
    Prev
    Next
    INDEX
    Explanations

    healthcare professionals and services

    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
    illi
    -0.22
    permalink
    -0.20
    åĻ¬
    -0.19
     Employ
    -0.19
    åķĨ家
    -0.19
    驼
    -0.19
    ç½ij绾èIJ¥éĶĢ
    -0.19
    æŃ£å¼ı
    -0.19
    çĿ£
    -0.19
    èĢģèĻİ
    -0.19
    POSITIVE LOGITS
    æ¹Ķ
    0.21
    å·¥ä½ľä¸Ń
    0.20
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.20
    asters
    0.19
    leep
    0.19
    æ²®
    0.18
    å¤įæŁ¥
    0.18
    isia
    0.18
    -sk
    0.18
     tact
    0.18
    Activations Density 0.169%

    No Known Activations