© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    transaction completion

    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
    chie
    -0.26
    éĨ
    -0.25
    æĿĥå¨ģ
    -0.25
    åģı
    -0.24
    _COMPILE
    -0.24
    æıŃ示
    -0.24
    kers
    -0.23
    Toggle
    -0.23
    丰å¯Į
    -0.23
    anchors
    -0.23
    POSITIVE LOGITS
     purchased
    0.50
    è´Ńä¹°
    0.48
     purchase
    0.48
     purchases
    0.46
     purchasing
    0.43
    ä¹°çļĦ
    0.42
     payment
    0.40
    ä»ĺ款
    0.40
     Purchase
    0.40
    購買
    0.39
    Activations Density 0.100%

    No Known Activations