© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12208
    Prev
    Next
    INDEX
    Explanations

    files and licenses

    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
     Oilers
    -0.19
    ilst
    -0.18
    ä»ĬåIJİ
    -0.18
    大ä¼ļ
    -0.18
    Moder
    -0.18
    æ·«
    -0.18
    èĢĮ对äºİ
    -0.18
    åĩł
    -0.17
    åĽłèĢĮ
    -0.17
    //:
    -0.17
    POSITIVE LOGITS
    otti
    0.20
    æĤ¬å´ĸ
    0.20
     ÑģÑĤоим
    0.20
    emento
    0.19
    éĴĵ
    0.19
     Fit
    0.19
    -fit
    0.19
    enge
    0.19
     ÑģÑĤанд
    0.18
    æ´ĹåĩĢ
    0.18
    Activations Density 0.002%

    No Known Activations