© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    FOR IMMEDIATE RELEASE

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.22
    诲
    -0.21
    ãĤªãĥªãĤ¸ãĥĬãĥ«
    -0.19
    ÑĮÑı
    -0.19
    交éĻħ
    -0.18
    éĽ¢éĸĭ
    -0.17
    è±Ĩçĵ£
    -0.17
    faces
    -0.17
    æĵĴ
    -0.17
    à¸ģารà¸Ĺำ
    -0.17
    POSITIVE LOGITS
    uil
    0.19
    plib
    0.18
    åѦåłĤ
    0.18
    sist
    0.18
    emed
    0.18
    ä¸ĬéŨ
    0.18
    åIJĪ约
    0.17
    å¹¢
    0.17
    é»ĺ
    0.17
    ogra
    0.17
    Activations Density 0.002%

    No Known Activations