© 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. 10957
    Prev
    Next
    INDEX
    Explanations

    rough, worn, crude, raw

    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
    æĨĭ
    -0.21
     Contr
    -0.19
    WND
    -0.19
    åįĴ
    -0.19
    rios
    -0.19
     Yüksek
    -0.19
    æĢ
    -0.18
    utex
    -0.18
    æ¡ī
    -0.18
    ueling
    -0.18
    POSITIVE LOGITS
    æķħæĦı
    0.30
    ç²Ĺç³Ļ
    0.29
    èĩªçĦ¶
    0.28
     rough
    0.27
     rustic
    0.26
    æľ´
    0.25
     naturally
    0.25
    ä¸įå¿į
    0.24
    ç²Ĺ
    0.24
    é£İæł¼
    0.24
    Activations Density 0.061%

    No Known Activations