© 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. 10787
    Prev
    Next
    INDEX
    Explanations

    formation, Earth's history, core

    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
    çĭ±
    -0.20
    æ¨Ĺ
    -0.20
    åİ¿éķ¿
    -0.20
     DEAD
    -0.19
    ä¸ĢåĪĨéĴŁ
    -0.19
    cci
    -0.19
    æĸ°äº§åĵģ
    -0.18
    被æī§è¡Į
    -0.18
     mens
    -0.18
    åħ»çĮª
    -0.18
    POSITIVE LOGITS
    åŃķèĤ²
    0.26
    æĹ©æľŁ
    0.23
    åŃ°
    0.23
    è¯ŀçĶŁ
    0.22
    uring
    0.21
    å¥łå®ļ
    0.21
    uch
    0.21
    genesis
    0.20
    ance
    0.20
    ordial
    0.20
    Activations Density 0.040%

    No Known Activations