© 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. 13635
    Prev
    Next
    INDEX
    Explanations

    lymph nodes and vessels

    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
    çģ«åĬĽ
    -0.22
    uers
    -0.20
    èIJ½ä¸ĭ
    -0.19
    é«ĺæĢ§èĥ½
    -0.19
    phia
    -0.17
    ards
    -0.17
    ModelError
    -0.17
    éĴĿ
    -0.17
    stand
    -0.16
    mination
    -0.16
    POSITIVE LOGITS
    ï¸ı
    0.21
    tic
    0.21
    çķĮçļĦ
    0.20
    ian
    0.20
    çķĮ
    0.19
    ç³»ç»ŁçļĦ
    0.18
    汩
    0.18
    éĢ¶
    0.18
     inval
    0.18
    ç¼ī
    0.18
    Activations Density 0.029%

    No Known Activations