© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    founder or founded

    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
    æĿ¥èĩª
    -0.28
    æĹ¥å¸¸
    -0.24
    ä¾Ĩèĩª
    -0.24
    viewer
    -0.22
     insets
    -0.22
    ãĥĥ
    -0.22
    è°¨æħİ
    -0.21
    éĩįéĩį
    -0.21
    åĩłåĪĨ
    -0.21
    logged
    -0.21
    POSITIVE LOGITS
     anew
    0.32
    ä¸İåıijå±ķ
    0.32
    ä¸Ģ个æĸ°çļĦ
    0.29
    åĴĮåıijå±ķ
    0.28
    OrUpdate
    0.28
    ä¹ĭåĪĿ
    0.28
    æĸĩæĺİåŁİå¸Ĥ
    0.28
    æĪIJç«ĭäºĨ
    0.27
    åĪĿè¡·
    0.25
    /cop
    0.25
    Activations Density 0.045%

    No Known Activations