© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    pretty + adjective

    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
    èѬå¦Ĥ
    -0.19
    æĽ´å¥½åľ°
    -0.17
    emaker
    -0.17
    orem
    -0.16
    éĤ£ä¹Īå¤ļ
    -0.15
    ï¸ı
    -0.15
    sv
    -0.15
    æĽ´å¤ļä¿¡æģ¯
    -0.15
    ä¸Ģ个éĹ®é¢ĺ
    -0.15
    Çİ
    -0.15
    POSITIVE LOGITS
    说æĺ¯
    0.20
     darn
    0.20
    äºĭåĦ¿
    0.19
    ä¸įéĶĻçļĦ
    0.19
    -boy
    0.18
    oting
    0.18
    ening
    0.18
    ä¸įå°ıçļĦ
    0.17
    -faced
    0.17
    ly
    0.16
    Activations Density 0.011%

    No Known Activations