© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    re- prefix

    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
    é«ĺæķĪçļĦ
    -0.23
    ç¢İçīĩ
    -0.20
    å¤ļåħĥ
    -0.20
    mins
    -0.19
     gi
    -0.18
    çİ°
    -0.18
    èī²ç´ł
    -0.18
    å¤ļåħĥåĮĸ
    -0.17
    æĻ®éĢļçļĦ
    -0.17
    èĩĨ
    -0.17
    POSITIVE LOGITS
    åľ¨åIJĮä¸Ģ
    0.26
    次æķ°
    0.26
    åĽŀæĿ¥
    0.21
    éĩįå¤į
    0.21
    æľºä¼ļ
    0.21
    /ref
    0.21
    踵
    0.21
    bidden
    0.21
    å¤ļ次
    0.20
    è¾Ħ
    0.20
    Activations Density 0.140%

    No Known Activations