© 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. 280
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and numbers

    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
    空æ°Ķè´¨éĩı
    -0.27
    åĭĥ
    -0.24
    湿度
    -0.23
    .threshold
    -0.23
    ird
    -0.23
    serter
    -0.23
    åīįä»»
    -0.22
    sizes
    -0.22
    ä¸Ģç¯ĩæĸĩç«ł
    -0.22
     threshold
    -0.22
    POSITIVE LOGITS
    æ··åIJĪ
    0.26
     cr
    0.25
    åıĬ
    0.24
    åĪ©
    0.24
    ä¿¡
    0.24
    åĴĮåħ¶ä»ĸ
    0.22
    åĴĮ
    0.22
    æ´§
    0.22
    plus
    0.22
    åħ¼
    0.22
    Activations Density 0.045%

    No Known Activations