© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    healthcare practitioners

    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
    ingly
    -0.19
    ByPrimaryKey
    -0.17
    ings
    -0.17
    å§Ķåī¯ä¹¦è®°
    -0.16
    ForKey
    -0.16
    ï¸ı
    -0.16
    tures
    -0.16
    æł·çļĦ
    -0.16
     воÑĤ
    -0.16
    adamente
    -0.15
    POSITIVE LOGITS
    ../../
    0.21
    ties
    0.20
    iated
    0.19
    ../../../
    0.18
    nels
    0.18
    èĢħçļĦ
    0.17
    ror
    0.17
    ials
    0.17
    ality
    0.17
    iate
    0.16
    Activations Density 0.010%

    No Known Activations