© 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. 15674
    Prev
    Next
    INDEX
    Explanations

    Clark Kent

    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
     Recover
    -0.19
     republic
    -0.19
     ÑĢайон
    -0.19
    ém
    -0.19
    笼
    -0.19
    è§ģè¯Ĩ
    -0.18
    icker
    -0.18
    cape
    -0.18
    çľ¼ä¸ĭ
    -0.18
    èµĦ
    -0.17
    POSITIVE LOGITS
    建çŃijå·¥ç¨ĭ
    0.20
    梳
    0.20
    OB
    0.18
    æļ¾
    0.18
    åħ¨æĹ¥
    0.18
    ÑĤиÑĢ
    0.18
    ita
    0.17
    æĽ¦
    0.17
    ht
    0.17
     teachings
    0.17
    Activations Density 0.001%

    No Known Activations