© 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. 13799
    Prev
    Next
    INDEX
    Explanations

    sponsors and awards

    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
    ä»ĭ
    -0.22
    าà¸ĩ
    -0.21
    æĺĶæĹ¥
    -0.19
    èĽĬ
    -0.19
    WhatsApp
    -0.19
    éŁŃèıľ
    -0.19
     ander
    -0.19
    æķĻè®Ń
    -0.19
    cling
    -0.19
    çĶ¨éĢĶ
    -0.18
    POSITIVE LOGITS
    èµŀåĬ©
    0.27
     sponsors
    0.24
    è¯
    0.23
     sponsor
    0.22
    .uri
    0.21
    éĢīæĭĶ
    0.21
    æĦıåIJij
    0.20
     Cool
    0.20
     sponsorship
    0.20
    æĿ¯
    0.20
    Activations Density 0.057%

    No Known Activations