© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 50
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation like colons and periods

    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
     cad
    -0.25
    Tests
    -0.25
    Steam
    -0.24
    steam
    -0.23
    _pad
    -0.23
    إص
    -0.23
    幺
    -0.23
    _tests
    -0.23
     testName
    -0.23
    Tester
    -0.23
    POSITIVE LOGITS
    è·Łè¸ª
    0.26
     Season
    0.26
    æ¯ıæľĪ
    0.25
     Complexity
    0.25
     Min
    0.24
    Month
    0.24
     Key
    0.24
     Region
    0.23
     palm
    0.23
    ç½Ĺ马
    0.23
    Activations Density 0.031%

    No Known Activations