© 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. 690
    Prev
    Next
    INDEX
    Explanations

    fat and nutritional information

    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
    åľ¨åIJĮä¸Ģ
    -0.25
    åı¦ä¸Ģ
    -0.24
     Kut
    -0.23
    ä¸Ģä¸ĸ
    -0.23
    交éĢļå·¥åħ·
    -0.23
    为ä»Ģä¹Īä¸į
    -0.23
    客æµģ
    -0.23
    PTR
    -0.22
    вод
    -0.22
    typings
    -0.22
    POSITIVE LOGITS
    åĵ¨
    0.25
    att
    0.23
    acin
    0.23
     Tactics
    0.22
     Servlet
    0.22
    å¼±åĬ¿
    0.21
    енÑĤ
    0.21
    èĻİ
    0.21
     cnn
    0.21
    åį®
    0.21
    Activations Density 0.001%

    No Known Activations