© 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. 1592
    Prev
    Next
    INDEX
    Explanations

    immigration appeals and illegal immigrants

    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
     Tight
    -0.28
    å¸ĥç½®
    -0.27
    éĥ½è§īå¾Ĺ
    -0.26
    é»ĺå¥ij
    -0.24
    template
    -0.24
    æĪIJåĬŁçļĦ
    -0.23
    çݯæ¯Ķ
    -0.23
    åįģåĪĨéĴŁ
    -0.23
    ortal
    -0.23
    æĦıåij³
    -0.23
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.29
    enef
    0.26
     currently
    0.25
     eligible
    0.25
    éķ¿æľŁ
    0.24
    å·²ç»ıåľ¨
    0.24
     pardon
    0.24
    å±ħä½ı
    0.23
    家ä½ı
    0.23
     criminal
    0.23
    Activations Density 0.015%

    No Known Activations