© 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. 10602
    Prev
    Next
    INDEX
    Explanations

    runway open, parachute or, noble gases

    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
    çİ°
    -0.23
    主è¦ģä»İäºĭ
    -0.20
    çijķ
    -0.20
    主è¦ģçĶ¨äºİ
    -0.20
    å°ıé¢Ŀ
    -0.20
    æĶ¯éĺŁ
    -0.19
    æIJľçĭIJé¦ĸ页
    -0.19
    >NN
    -0.19
    积æŀģæݨåĬ¨
    -0.19
    çĥŃçĤ¹
    -0.19
    POSITIVE LOGITS
    enta
    0.22
    æīįä¼ļ
    0.20
    ru
    0.20
    人çĶŁçļĦ
    0.20
    æĿµ
    0.19
    éķ¿èĢģ
    0.19
    EOS
    0.19
     lif
    0.19
     prototype
    0.18
     Gandhi
    0.18
    Activations Density 0.113%

    No Known Activations