© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10565
    Prev
    Next
    INDEX
    Explanations

    Miville, Gurtina, Gurtovoy

    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
    Negative Logits
    æģ¬
    -0.20
    åłĻ
    -0.19
    STEM
    -0.18
     Undefined
    -0.18
     Merr
    -0.17
    istani
    -0.17
    ä¸į足
    -0.17
     Paging
    -0.17
    ราà¸Ĭ
    -0.17
    rox
    -0.16
    POSITIVE LOGITS
    æijĬ
    0.18
    quier
    0.17
    æĮij
    0.17
    æİĽãģij
    0.17
    ãģªãģıãģ¦
    0.17
    交èŀį
    0.16
    é¤į
    0.16
    HING
    0.16
     ÐĶмиÑĤÑĢ
    0.16
    gel
    0.16
    Activations Density 0.243%

    No Known Activations