© 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. 15182
    Prev
    Next
    INDEX
    Explanations

    for the

    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
     ÐŁÐ¾Ñĩем
    -0.39
     ÐIJлекÑģан
    -0.39
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.33
     ÐĶмиÑĤÑĢ
    -0.32
    ÑĩÑĢежден
    -0.31
    à¸Ħà¸ĵะà¸ģรรม
    -0.31
    à¹Ĥรà¸ĩà¸ŀยา
    -0.30
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.30
    à¸Ħะà¹ģà¸Ļ
    -0.29
    индивид
    -0.29
    POSITIVE LOGITS
     the
    0.44
    ìĿĺ
    0.35
    æĺĢ
    0.32
    _the
    0.30
    the
    0.29
    The
    0.28
    ãģ®
    0.28
    çļĦ
    0.27
    ìĿľ
    0.27
    çļĦæĪIJéķ¿
    0.26
    Activations Density 1.113%

    No Known Activations