© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16979
    Prev
    Next
    INDEX
    Explanations

    petroleum, oil, crude, ore, coke

    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
    âīĤ
    -0.24
    *sp
    -0.21
    éĵĪ
    -0.20
    åħ¬æ°ij
    -0.20
    localized
    -0.20
    ä¸ĵèģĮ
    -0.19
     HOLDER
    -0.18
    æł¡å¤ĸ
    -0.18
    éķ±
    -0.18
    ä¹ĭ人
    -0.18
    POSITIVE LOGITS
    产åĩº
    0.28
    éĻĦåĬłåĢ¼
    0.27
    åİŁæ²¹
    0.24
    ä»·åĢ¼éĵ¾
    0.24
    åĽłåľ°
    0.22
    å¼Ģéĩĩ
    0.21
    æ²»çIJĨä½ĵç³»
    0.20
     اÙĦخاÙħ
    0.20
    æ²®
    0.20
    å·¥ä¸ļ
    0.20
    Activations Density 0.042%

    No Known Activations