© 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. 16426
    Prev
    Next
    INDEX
    Explanations

    introduction or preface

    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
    ssi
    -0.24
    ḿ
    -0.18
     gratuit
    -0.18
     QIcon
    -0.18
     SCE
    -0.18
    æĶ¾å¿ĥ
    -0.17
    THEN
    -0.17
    irts
    -0.17
    å´Ĩ
    -0.17
    MENU
    -0.17
    POSITIVE LOGITS
    æĬĬæĪij
    0.23
    æĪijèĩªå·±
    0.23
     myself
    0.21
    è¿Ļ个éĹ®é¢ĺ
    0.21
    æĿ¥è¿ĻéĩĮ
    0.21
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.20
    è¿Ļç¯ĩ
    0.20
    对æĪij
    0.20
    亲çĪ±
    0.20
    éĹ®æĪij
    0.19
    Activations Density 1.141%

    No Known Activations