© 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. 13864
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals and medication

    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
    èIJĿåįľ
    -0.23
    å¾Ń
    -0.22
    peat
    -0.21
     Carbon
    -0.19
     Conveyor
    -0.19
    éļĪ
    -0.19
    åħ¨æĹ¥åĪ¶
    -0.18
     Alloy
    -0.18
     Carnegie
    -0.18
     Credits
    -0.17
    POSITIVE LOGITS
    æ¯Ĵåĵģ
    0.29
    èį¯åĵģ
    0.28
    èį¯çī©
    0.24
    èĹ¥
    0.24
    ä¿Ŀ管
    0.24
    èį¯
    0.23
    å®īåħ¨æĦŁ
    0.22
    éĤ»éĩĮ
    0.22
     unsafe
    0.22
    çģ¿
    0.22
    Activations Density 0.010%

    No Known Activations