© 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. 924
    Prev
    Next
    INDEX
    Explanations

    monopoly powers and board games

    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
    ena
    -0.24
    apon
    -0.23
    ajas
    -0.22
    apur
    -0.22
    ataka
    -0.22
    ampion
    -0.22
    ä»»ä½ķå½¢å¼ı
    -0.22
    ç«ĭéĿ¢
    -0.21
     pragma
    -0.21
     unn
    -0.20
    POSITIVE LOGITS
    iens
    0.26
    æĢ§çĸ¾çĹħ
    0.23
    座
    0.23
    Street
    0.23
    ä¹ĭè·¯
    0.22
    ä½ĵç³»
    0.22
     вла
    0.21
    plate
    0.21
     доÑħод
    0.21
    health
    0.21
    Activations Density 0.004%

    No Known Activations