© 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. 2666
    Prev
    Next
    INDEX
    Explanations

    different followed by a noun

    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
    ä¸İåħ¶ä»ĸ
    -0.23
    ħ§
    -0.23
     "***
    -0.23
    çħ§
    -0.22
    æĥħèĬĤ
    -0.22
    accine
    -0.22
     unbiased
    -0.22
     Powder
    -0.22
     itself
    -0.22
     versus
    -0.21
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.52
    åIJĦèĩª
    0.44
    ãģĿãĤĮãģŀãĤĮ
    0.34
     respectively
    0.31
    åIJĦæľī
    0.31
    äºĴè¡¥
    0.30
    åĪĨåĪ«æĺ¯
    0.29
     respective
    0.29
    æľīä¸įåIJĮçļĦ
    0.29
    ä¸įåIJĮçļĦ
    0.28
    Activations Density 0.114%

    No Known Activations