© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 193
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    ,
    -0.40
     at
    -0.34
     en
    -0.32
    ;
    -0.32
    ed
    -0.32
     in
    -0.31
    :
    -0.31
    -0.31
     to
    -0.31
    es
    -0.30
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.35
     ÐĶмиÑĤÑĢ
    0.28
     ÐŁÐ¾Ñĩем
    0.27
    éĩijèŀįæľįåĬ¡
    0.26
    canonical
    0.25
    çİ°å®ŀçĶŁæ´»
    0.25
    ä¸¥æł¼
    0.24
    è¯ģåĪ¸äº¤æĺĵ
    0.23
     наÑĢко
    0.23
    successfully
    0.23
    Activations Density 2.220%

    No Known Activations