© 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. 13227
    Prev
    Next
    INDEX
    Explanations

    online registration or booking

    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
     Chapman
    -0.20
    yc
    -0.19
    unde
    -0.18
    dex
    -0.18
    Ing
    -0.18
     def
    -0.18
    coma
    -0.17
    穷人
    -0.17
     ecology
    -0.17
    æĥħ
    -0.17
    POSITIVE LOGITS
    jur
    0.20
    ä¸įæĸ¹ä¾¿
    0.19
    èIJ¥éĢłèī¯å¥½
    0.19
    责任åĪ¶
    0.19
    è°Ĵ
    0.19
    aisy
    0.18
    æĮĩ导æĦıè§ģ
    0.18
    è¿Ļç§įæĸ¹æ³ķ
    0.18
     Alone
    0.18
    owie
    0.18
    Activations Density 0.015%

    No Known Activations