© 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. 2672
    Prev
    Next
    INDEX
    Explanations

    chapters and sections

    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
    çŀ¬
    -0.30
    çŀ¬éĹ´
    -0.25
    端
    -0.25
    ä¸įåľ¨
    -0.25
     nowhere
    -0.25
    è¢ĭ
    -0.24
    毫
    -0.24
    ä½İæĪIJæľ¬
    -0.24
    -loving
    -0.24
    çıŃ
    -0.24
    POSITIVE LOGITS
     chapters
    0.54
     sections
    0.48
    ç«łèĬĤ
    0.48
    ç¯ĩç«ł
    0.44
     thematic
    0.41
     Chapters
    0.40
    çļĦ主é¢ĺ
    0.38
    sections
    0.37
    主æŨ
    0.37
     themes
    0.36
    Activations Density 0.067%

    No Known Activations