© 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. 438
    Prev
    Next
    INDEX
    Explanations

    saying "i know" or "you know"

    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
     Contrib
    -0.24
     cohesion
    -0.23
    osti
    -0.22
    åĢ¼å¾Ĺ
    -0.22
     permanent
    -0.22
     Lug
    -0.22
     IP
    -0.22
     perman
    -0.22
     integrated
    -0.21
    .processor
    -0.21
    POSITIVE LOGITS
    åıį驳
    0.35
    æī¹è¯Ħ
    0.30
    ä¸įçĽ¸ä¿¡
    0.30
     critiques
    0.28
    æijĩ头
    0.28
    åIJ¬å®Į
    0.27
    ä¸įåIJĮæĦı
    0.27
    è·ŁæĪij说
    0.27
     arguments
    0.26
     criticize
    0.26
    Activations Density 0.055%

    No Known Activations