© 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. 16257
    Prev
    Next
    INDEX
    Explanations

    listicle items

    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
    åĽ¿
    -0.20
    åIJ¦
    -0.19
    深交
    -0.19
    ä¼į
    -0.18
    eland
    -0.18
    uyá»ģn
    -0.18
    .timestamps
    -0.18
    æį®
    -0.18
    ä¹ĭåīįçļĦ
    -0.18
     vo
    -0.17
    POSITIVE LOGITS
    æķĻä½ł
    0.21
    åħ³éĶ®æŶåĪ»
    0.20
    éĻªçĿĢ
    0.20
    æģ¶
    0.20
     ÑģпоÑģоб
    0.20
    çIJĨçĶ±
    0.19
    æ£Ģ
    0.19
     ways
    0.19
     @@
    0.18
    =top
    0.18
    Activations Density 0.037%

    No Known Activations