© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    button, options, or register

    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¸į说
    -0.19
    ç»ĺåĪ¶
    -0.19
    éĺĨ
    -0.19
    ENA
    -0.19
    ä¸Ģåij³
    -0.18
    常说
    -0.18
    çĪ¶
    -0.18
    åį´ä¸į
    -0.18
    ä¼Ĺ
    -0.18
    ä¸įåIJĥ
    -0.18
    POSITIVE LOGITS
    æĮīéĴ®
    0.21
     buttons
    0.21
    èıĬ
    0.21
     button
    0.21
    button
    0.20
     кноп
    0.19
    elman
    0.19
    åľ¨è·¯ä¸Ĭ
    0.19
     Bermuda
    0.19
    éĢī项
    0.19
    Activations Density 0.033%

    No Known Activations