© 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. 269
    Prev
    Next
    INDEX
    Explanations

    programming directives, math symbols, simplification

    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
    lei
    -0.25
    èªī
    -0.22
     Tart
    -0.21
    å¾Ģå¤ĸ
    -0.21
     replicas
    -0.21
    è¯
    -0.21
     tiers
    -0.21
     replica
    -0.20
     пол
    -0.20
    eller
    -0.20
    POSITIVE LOGITS
    åĨįä¸Ģ次
    0.25
     Again
    0.23
     again
    0.23
    åĨį次
    0.23
    éĺ¿å¯Į
    0.22
    creen
    0.22
    å·´èı²
    0.21
    ilogy
    0.21
     novamente
    0.21
    寥
    0.21
    Activations Density 0.012%

    No Known Activations