© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 655
    Prev
    Next
    INDEX
    Explanations

    non-small cell lung carcinoma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    èĬ
    -0.25
     Concrete
    -0.24
     ach
    -0.23
     concrete
    -0.23
    Concrete
    -0.22
    款
    -0.22
    apr
    -0.22
    Currency
    -0.21
     alike
    -0.21
    orda
    -0.21
    POSITIVE LOGITS
    ä¸Ģå¼ł
    0.27
    é«ĺåĩº
    0.24
    æłĩæĺİ
    0.23
     Nodo
    0.23
    è¾ĥå°ı
    0.21
     glu
    0.21
    åıªæľīä¸Ģ个
    0.21
    æ°ij主çĶŁæ´»
    0.21
    ä¸¤å¼ł
    0.21
     Minority
    0.21
    Activations Density 0.002%

    No Known Activations