© 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. 14469
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    æĪIJåĬŁçļĦ
    -0.25
    å¾Īå¤ļäºĭæĥħ
    -0.24
    åIJĮäºĭ们
    -0.21
    æĪIJåĬŁä¸¾åĬŀ
    -0.21
    ä¸Ĭæ¼Ķ
    -0.21
    è§ģè¯ģäºĨ
    -0.21
    åħ»èĢģéĩij
    -0.21
    æĪijåĸľæ¬¢
    -0.21
    åĽłä¸ºæĪij
    -0.21
    羣çļĦæĺ¯
    -0.20
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.25
    à¹Ģà¸Ĺศà¸ģา
    0.25
     specified
    0.25
    åħľ
    0.23
    æģ«
    0.23
    æĿĵ
    0.22
     specifies
    0.22
    pecified
    0.22
    aland
    0.22
    æ§Ľ
    0.21
    Activations Density 0.074%

    No Known Activations