© 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. 1693
    Prev
    Next
    INDEX
    Explanations

    financial accounting and reports

    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
     tight
    -0.23
    otine
    -0.23
    .unlock
    -0.23
    çıł
    -0.22
    éĽķåĪ»
    -0.22
    اث
    -0.22
    .radius
    -0.22
    Radius
    -0.21
    çŃ·åŃIJ
    -0.21
    /small
    -0.21
    POSITIVE LOGITS
    èµĦäº§è´ŁåĢº
    0.37
     sheet
    0.33
    heet
    0.31
    æĬ¥è¡¨
    0.28
    çľĭä»ĸ
    0.28
    åĪĨæŀIJ
    0.28
    è´ŁåĢº
    0.28
    -sheet
    0.28
    æ¸ħåįķ
    0.27
     chart
    0.27
    Activations Density 0.034%

    No Known Activations