© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    rumor

    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
     Airways
    -0.20
    .viewmodel
    -0.19
    注æĦıåĬĽ
    -0.19
    ä¸įäºĨ
    -0.18
    yı
    -0.17
    ymoon
    -0.17
    è¿Ļ对
    -0.17
    èİ«åIJįåħ¶å¦Ļ
    -0.17
    æĸ°éĹ»ç½ij
    -0.16
    erness
    -0.16
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.30
    å·²ä¹ħ
    0.24
    ìĤ¬íķŃ
    0.19
    -proof
    0.19
    ously
    0.18
    ably
    0.18
    anges
    0.17
     about
    0.17
    ä¸įå·²
    0.16
    acle
    0.16
    Activations Density 0.008%

    No Known Activations