© 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. 14987
    Prev
    Next
    INDEX
    Explanations

    inflammatory bowel diseases

    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
    赡
    -0.20
    èĢģ人
    -0.20
     Repos
    -0.19
    è´ŀ
    -0.19
    èĢģ人家
    -0.19
    æŀĦ
    -0.19
    /Runtime
    -0.19
    嫦
    -0.19
    (objects
    -0.18
     Retirement
    -0.18
    POSITIVE LOGITS
    cycle
    0.23
     kosher
    0.21
     Friedman
    0.20
    æ²ħ
    0.19
    bara
    0.18
     cycles
    0.18
    å°»
    0.18
    å¼Ł
    0.18
    uj
    0.17
    (AP
    0.17
    Activations Density 0.042%

    No Known Activations