© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    cemetery and burial sites

    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
    UBE
    -0.31
    ube
    -0.30
    æĢģ
    -0.25
    诱
    -0.24
    ä¾µçķ¥
    -0.24
    çĭİ
    -0.23
     lakh
    -0.23
    è°²
    -0.22
    èĢĮçİ°åľ¨
    -0.22
    _STREAM
    -0.22
    POSITIVE LOGITS
     cemetery
    0.50
     Cemetery
    0.48
    å¢ĵ
    0.42
    åĿŁ
    0.33
     graveyard
    0.33
     burial
    0.32
     crem
    0.30
     ceremonies
    0.28
     chapel
    0.28
    æĮĩå®ļ
    0.28
    Activations Density 0.002%

    No Known Activations