© 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. 11795
    Prev
    Next
    INDEX
    Explanations

    absolutely followed by adjective

    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
     zwar
    -0.18
    æĽ´å¥½åľ°
    -0.17
    èµ·åĪĿ
    -0.17
    åį³ä½¿
    -0.17
    older
    -0.17
    ä½łè§īå¾Ĺ
    -0.17
    æ¯ķç«Ł
    -0.17
    /her
    -0.17
    å¦Ĥæŀľä¸į
    -0.17
    allocator
    -0.16
    POSITIVE LOGITS
    -minded
    0.25
    ìłģìĿ¸
    0.20
    mente
    0.20
    ãģ¨ãģĦãģ£ãģ¦
    0.20
     minded
    0.19
    个å¤ļ
    0.19
    æĦıä¹īä¸ĬçļĦ
    0.19
    zing
    0.17
     nothing
    0.17
    ities
    0.17
    Activations Density 0.014%

    No Known Activations