© 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. 15665
    Prev
    Next
    INDEX
    Explanations

    recurrence, continuing, addressed

    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
    说äºĨ
    -0.22
     drops
    -0.22
    æĶ¶åĪ°äºĨ
    -0.20
    åĿĩè¡¡
    -0.20
    æľīåIJįçļĦ
    -0.20
    主å¸Ń
    -0.20
    æļĿ
    -0.19
     concert
    -0.19
    ä¸įéĶĻçļĦ
    -0.19
     Blaze
    -0.19
    POSITIVE LOGITS
    继ç»Ń
    0.28
    åĨį次
    0.28
    éļIJæĤ£
    0.25
     continue
    0.25
     continuing
    0.24
     continues
    0.23
    åĨį度
    0.23
    åľ¨æľªæĿ¥
    0.23
     continued
    0.23
    延ç»Ń
    0.23
    Activations Density 0.163%

    No Known Activations