© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1373
    Prev
    Next
    INDEX
    Explanations

    amount to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     accompanying
    -0.22
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.22
    ãģĿãĤĮãģ«
    -0.22
    主任
    -0.20
     upcoming
    -0.20
    ä¸ĵ注äºİ
    -0.20
    缸åħ³åĨħ容
    -0.20
     overst
    -0.20
    èģĶç³»æĸ¹å¼ı
    -0.20
     обÑĢаÑī
    -0.19
    POSITIVE LOGITS
    ä¸įå°ıçļĦ
    0.29
    ä¸ĢåĽŀäºĭ
    0.29
    ä»Ģä¹Īåij¢
    0.26
    IgnoreCase
    0.26
    ä¸įå°ı
    0.24
    ingly
    0.23
    ä¸ĩåįĥ
    0.23
    æŀģ大çļĦ
    0.23
    ä¸įéĶĻçļĦ
    0.23
    å¾Īé«ĺçļĦ
    0.23
    Activations Density 0.010%

    No Known Activations