© 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. 17063
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    Negative Logits
    çĶ¨æīĭ
    -0.22
     sed
    -0.20
    xDC
    -0.20
    comp
    -0.20
    رÙĬÙģ
    -0.20
    pseudo
    -0.19
    çıħ
    -0.19
    æıª
    -0.19
    èĥİ
    -0.19
    pill
    -0.19
    POSITIVE LOGITS
    è§Ħå®ļçļĦ
    0.29
    è¡Įäºĭ
    0.26
     rules
    0.26
    åIJĦ项
    0.25
    缸åħ³è§Ħå®ļ
    0.25
    è§Ħç«łåĪ¶åº¦
    0.25
    gMaps
    0.25
    åĽ½å®¶æłĩåĩĨ
    0.24
    çļĦåIJĦ项
    0.24
    éļıæŶ
    0.23
    Activations Density 0.154%

    No Known Activations