© 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. 11549
    Prev
    Next
    INDEX
    Explanations

    medical devices and equipment

    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
    æįī
    -0.24
    æĮ¨
    -0.20
    åIJĦè¡Į
    -0.20
    éħĴä¸ļ
    -0.20
    åħ¨åŁŁæĹħ游
    -0.20
    èĶ·
    -0.19
    åij³
    -0.19
    oney
    -0.19
    éĢļ车
    -0.19
    è¿ĩå¤ļ
    -0.19
    POSITIVE LOGITS
    åĻ¨æ¢°
    0.25
    å®ŀçī©
    0.24
    械
    0.22
     изделиÑı
    0.21
    åĮ»çĸĹåĻ¨æ¢°
    0.21
     издели
    0.20
     equipment
    0.20
    设å¤ĩ
    0.19
     medical
    0.18
    eps
    0.18
    Activations Density 0.051%

    No Known Activations