© 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. 14167
    Prev
    Next
    INDEX
    Explanations

    yogurt, cheese, avocado, defaults

    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
    DTD
    -0.19
    æĸ°æĿIJæĸĻ
    -0.19
    .organ
    -0.18
    们
    -0.18
    åħ¶ä»ĸçļĦ
    -0.17
    values
    -0.17
    hai
    -0.17
    Serialized
    -0.17
    uilt
    -0.17
    社ä¼ļå®ŀè·µ
    -0.17
    POSITIVE LOGITS
     Kut
    0.19
    enton
    0.18
    éºĴ
    0.18
    ä¸ĭæ»ij
    0.18
     пÑıÑĤ
    0.18
    erde
    0.18
    Slim
    0.18
    æĹłäººæľº
    0.18
     grop
    0.18
     acos
    0.18
    Activations Density 0.001%

    No Known Activations