© 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. 711
    Prev
    Next
    INDEX
    Explanations

    comparing to average or usual

    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
    å°±è¿ij
    -0.27
    ä¸įçķĻ
    -0.24
    åĪ¶åº¦æĶ¹éĿ©
    -0.23
     increasingly
    -0.22
     Paste
    -0.22
    缸åħ³æĶ¿çŃĸ
    -0.22
    çѵ
    -0.22
    æĹłç¼Ŀ
    -0.21
    ugs
    -0.21
     Synopsis
    -0.21
    POSITIVE LOGITS
     amount
    0.26
    è¿Ļæĺ¯åĽłä¸º
    0.24
    çĶ±äºİ
    0.24
    çļĦçĥŃæĥħ
    0.24
    ä½¼
    0.23
    -security
    0.23
    çĥŃæĥħ
    0.23
     (>
    0.23
    usual
    0.22
     due
    0.22
    Activations Density 0.033%

    No Known Activations