© 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. 2939
    Prev
    Next
    INDEX
    Explanations

    company founded or Inc

    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
     Tradition
    -0.27
     Yugosl
    -0.26
     tradition
    -0.25
     ÑħозÑıй
    -0.24
     format
    -0.24
    Decoration
    -0.24
    styleType
    -0.24
     COMMENTS
    -0.24
     recreation
    -0.23
     traditions
    -0.23
    POSITIVE LOGITS
    åĪĿåĪĽ
    0.46
    èĩªä¸»çłĶåıij
    0.42
    åħ¬åı¸çļĦ
    0.40
    æł¸å¿ĥæĬĢæľ¯
    0.38
     Technologies
    0.38
    æĪIJç«ĭäºİ
    0.38
    æĪIJç«ĭ
    0.37
    åħ¬åı¸
    0.37
    è¿Ļ家åħ¬åı¸
    0.37
     startups
    0.37
    Activations Density 0.173%

    No Known Activations