© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    news sources and financial analysis

    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
    çĽ²çĽ®
    -0.26
    仨
    -0.25
    æĶ¹å»º
    -0.24
     fundamentally
    -0.23
    ohon
    -0.23
    讲
    -0.23
    è¬Ľ
    -0.23
    代表大ä¼ļ
    -0.22
    perimental
    -0.22
    zell
    -0.22
    POSITIVE LOGITS
    çĭ¬å®¶
    0.35
    èµĦæĸĻæĺ¾ç¤º
    0.30
    æķ´çIJĨ
    0.29
    ç»Łè®¡
    0.28
     calculations
    0.28
    åĪĨæŀIJå¸Ī
    0.27
     aggreg
    0.26
    æķ°æį®æĺ¾ç¤º
    0.26
    è·Łè¸ª
    0.25
    å®ŀæŶ
    0.25
    Activations Density 0.010%

    No Known Activations