© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12505
    Prev
    Next
    INDEX
    Explanations

    aspirin and chloroquine

    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
    hog
    -0.24
    è§Ī
    -0.21
    çĢij
    -0.21
    æ®ĸ
    -0.20
    roma
    -0.19
    å¸Ĥåİ¿
    -0.19
    èĻ¹
    -0.19
    æĿ¼
    -0.19
    rese
    -0.18
    éľĵ
    -0.18
    POSITIVE LOGITS
    çļĦåĬŁæķĪ
    0.21
    Advertisements
    0.19
    arel
    0.19
    ´Ģ
    0.18
    æĥľ
    0.18
    æĹ¶ä»£çļĦ
    0.18
     pimp
    0.18
    ä½İå»ī
    0.18
    天æīį
    0.18
    coni
    0.18
    Activations Density 0.024%

    No Known Activations