© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1878
    Prev
    Next
    INDEX
    Explanations

    searching for a while

    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¨ģåĬĽ
    -0.26
    常常
    -0.25
     traditionally
    -0.24
    æºIJæºIJ
    -0.24
    ç»ı常
    -0.24
     commonly
    -0.23
    ä¸Ģçľ¼
    -0.23
    å°ļ
    -0.23
    æ°¸ä¹ħ
    -0.23
     currently
    -0.23
    POSITIVE LOGITS
     Eventually
    0.31
    ç»Īäºİ
    0.30
    ä¸Ģçķª
    0.30
     finally
    0.29
    å¼Ħ
    0.28
    è¾Ĺ转
    0.28
    åĩłæ¬¡
    0.27
    æĽ²æĬĺ
    0.27
    çºłç»ĵ
    0.27
    å¼Ħå¾Ĺ
    0.27
    Activations Density 0.111%

    No Known Activations