© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    low-fat food and diet

    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
    ering
    -0.21
    Matchers
    -0.20
    ibir
    -0.19
    éĶ¹
    -0.19
    itters
    -0.18
    æĥķ
    -0.17
    åĢĭ
    -0.17
     Hom
    -0.17
    ä¸Ģåı£
    -0.17
    esz
    -0.17
    POSITIVE LOGITS
    åĭĩæķ¢
    0.24
    飬
    0.23
    èĭ±åĭĩ
    0.23
    主ä¹ī
    0.21
    ç©°
    0.20
    åīįä¸Ģ天
    0.18
     Courage
    0.18
    icons
    0.18
    strategy
    0.18
    asia
    0.18
    Activations Density 0.003%

    No Known Activations