© 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. 12661
    Prev
    Next
    INDEX
    Explanations

    medical terminology, procedures, and conditions

    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
    å¹´ä¹ĭ
    -0.23
    ç½®
    -0.19
    ä¸ĵåĮº
    -0.18
    ek
    -0.18
    éħįéĢģ
    -0.17
    çĩĶ
    -0.17
    erah
    -0.17
    optic
    -0.17
     proj
    -0.17
    æµħ
    -0.17
    POSITIVE LOGITS
     Henderson
    0.20
    ·æĸ°
    0.20
    pressions
    0.20
    olley
    0.19
    ä¸įå¼Ģ
    0.19
     dol
    0.18
    ness
    0.18
    åĩºæīĭ
    0.18
    转
    0.18
    åİ¿åŁŁ
    0.18
    Activations Density 0.005%

    No Known Activations