© 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. 16647
    Prev
    Next
    INDEX
    Explanations

    habitat type

    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
    âīĤ
    -0.26
    âĨĽ
    -0.22
    âī½
    -0.21
    adian
    -0.21
    âĦ®
    -0.20
    é²Ī
    -0.20
    åĸĬ
    -0.20
    otech
    -0.20
    abus
    -0.20
    atitude
    -0.20
    POSITIVE LOGITS
    éĢļ常æĺ¯
    0.28
    æĿ¡ä»¶
    0.24
     environments
    0.23
    çݯå¢ĥ
    0.23
    è´´è¿ij
    0.23
    æľīä¸Ģå®ļ
    0.22
     ÑĥÑģловиÑı
    0.22
    çݯå¢ĥä¸Ń
    0.22
    ä¸Ĭå¹´
    0.22
    æĢ§å¼º
    0.22
    Activations Density 0.125%

    No Known Activations