© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    more information

    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
     ÐĶмиÑĤÑĢ
    -0.28
     ÐŁÐ¾Ñĩем
    -0.28
     ÐIJлекÑģан
    -0.28
    大éĩı
    -0.27
    ä¸įåIJĮçļĦ
    -0.25
     disc
    -0.23
    индивид
    -0.23
    æİī
    -0.23
    ä¸įåIJĮ
    -0.23
    пÑĢакÑĤик
    -0.23
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.26
    /power
    0.26
    æѤäºĭ
    0.26
    åĴĮæĶ¯æĮģ
    0.24
    é¾Ľ
    0.23
    社ä¼ļæķĪçĽĬ
    0.23
    /control
    0.23
    /help
    0.23
    è§Ĭ
    0.23
    /change
    0.23
    Activations Density 0.018%

    No Known Activations