© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    any

    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
    éĴ
    -0.20
     only
    -0.20
    çĦī
    -0.20
     properties
    -0.19
    ç¡®
    -0.17
     altern
    -0.17
    #region
    -0.17
    ort
    -0.17
    为ä¼ģä¸ļ
    -0.17
     marks
    -0.17
    POSITIVE LOGITS
    ä¸Ģ个å¤ļ
    0.21
    éĥ½è¦ģ
    0.20
     erfolgre
    0.20
    æĪIJåĬŁçļĦ
    0.20
    loat
    0.20
    ä¸įä½İäºİ
    0.20
    Regardless
    0.19
    successful
    0.19
    udent
    0.19
    çłĶ究æīĢ
    0.19
    Activations Density 0.066%

    No Known Activations