© 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. 16291
    Prev
    Next
    INDEX
    Explanations

    unipolar, unilateral, single component

    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
    ä¸įå°ij人
    -0.20
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.20
    æĽ´å¤ļçļĦ
    -0.19
    ä¸įä¸Ģæł·çļĦ
    -0.19
    ä¸ĢèĪ¬çļĦ
    -0.18
    ä¸įåIJĮçļĦ
    -0.18
    ä¹Łæľīä¸ĢäºĽ
    -0.17
    esda
    -0.17
    -dem
    -0.16
    ä¸Ģå®ļçļĦ
    -0.16
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.39
    /single
    0.29
    (single
    0.27
     лиÑĪÑĮ
    0.23
    tons
    0.23
    ìĶ©
    0.21
    ToOne
    0.21
    ida
    0.21
    æī¼
    0.20
    utow
    0.20
    Activations Density 0.109%

    No Known Activations