© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    MacBook Airs, respectively

    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
     its
    -0.26
     YOUR
    -0.23
    onto
    -0.23
    its
    -0.23
    fel
    -0.23
    åĽłä¸ºå®ĥ
    -0.23
    çľ¾
    -0.23
    æĺ¯ä¸Ģ项
    -0.22
    纷
    -0.22
    ))^
    -0.21
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.60
    åĪĨåĪ«æĺ¯
    0.57
     respectively
    0.56
    åĪĨåĪ«
    0.55
    åĪĨåĪ¥
    0.51
    åIJĦèĩªçļĦ
    0.48
    å®ĥ们
    0.45
    åIJĦèĩª
    0.45
     respective
    0.45
    ä¸įåIJĮç¨ĭ度
    0.40
    Activations Density 0.500%

    No Known Activations