© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    the biggest of the three

    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
    è¯ĥ
    -0.26
    æŃ£æĺ¯
    -0.25
    gün
    -0.23
    好ãģįãģª
    -0.22
    aph
    -0.22
    ensed
    -0.22
     exactly
    -0.21
    izz
    -0.21
    便ä¼ļ
    -0.21
    æĮĩ
    -0.21
    POSITIVE LOGITS
    å¹³åĿĩæ°´å¹³
    0.26
    ä¸ŃæľĢ
    0.24
    Located
    0.24
    æľĢ容æĺĵ
    0.24
    åIJĮæľŁ
    0.24
     Amid
    0.24
    éĩįä¸Ńä¹ĭ
    0.23
    æĢ»èĢĮè¨Ģä¹ĭ
    0.23
    ä»»ä½ķä¸Ģ个
    0.23
     bunch
    0.23
    Activations Density 0.092%

    No Known Activations