© 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. 12742
    Prev
    Next
    INDEX
    Explanations

    cases & instances

    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
    çļĦè¯Ŀé¢ĺ
    -0.21
    åľ¨è¿ĻéĩĮ
    -0.19
    noop
    -0.19
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    -0.19
    ä»Ģä¹Īéĥ½ä¸į
    -0.19
    ä¸Ģä¼ļåĦ¿
    -0.18
    没åħ³ç³»
    -0.18
    ä¹ĭæīĢ
    -0.18
    cloth
    -0.18
    tex
    -0.18
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.33
    æĥħå½¢
    0.33
    æĥħåĨµ
    0.32
     situations
    0.26
     ÑģлÑĥÑĩа
    0.25
     case
    0.25
    è¿Ļç§įæĥħåĨµ
    0.25
     cases
    0.25
     circumstances
    0.24
    æĥħæ³ģ
    0.24
    Activations Density 0.132%

    No Known Activations