© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    code clarity and readability

    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
    åħ¨å¥Ĺ
    -0.25
     Outreach
    -0.23
    åīįä»»
    -0.22
    æ½ľ
    -0.21
    éĺĻ
    -0.20
    conda
    -0.20
    covers
    -0.20
    cover
    -0.20
    è¿Ļå¥Ĺ
    -0.20
    orks
    -0.20
    POSITIVE LOGITS
    æĺ¾å¾Ĺ
    0.23
    èĪħ
    0.22
    绣ä¸Ģ
    0.21
    ä¼łéĢĴ
    0.21
    å°ıåIJĥ
    0.21
    æĸ¹ä¾¿
    0.21
    åıį转
    0.20
    ç¼ĸåĨĻ
    0.20
    表达
    0.20
    éĻĪè¿°
    0.20
    Activations Density 0.750%

    No Known Activations