© 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. 12685
    Prev
    Next
    INDEX
    Explanations

    binding

    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
    CESS
    -0.21
    LU
    -0.19
    åıĭåĸĦ
    -0.19
    é¦Ĺ
    -0.19
    çĻĸ
    -0.18
    輩
    -0.18
    å¢Ł
    -0.18
     обÑĭ
    -0.18
    ãĥģãĥ¥
    -0.18
    eg
    -0.18
    POSITIVE LOGITS
    åľ°ä½į
    0.23
    æĢ§çļĦ
    0.22
    æī§è¡ĮåĬĽ
    0.22
    ä»ħ次äºİ
    0.20
    ible
    0.20
    ä¸įäºĨ
    0.20
    æĸĩ书
    0.20
    çĶŁæķĪ
    0.19
    æĢ§å¼º
    0.19
    ardi
    0.19
    Activations Density 0.031%

    No Known Activations