© 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. 2419
    Prev
    Next
    INDEX
    Explanations

    applies or introduces conditions

    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
    æĬĬå®ĥ
    -0.36
    让å®ĥ
    -0.32
    åĴĮä»ĸçļĦ
    -0.26
    ä»İæĿ¥æ²¡æľī
    -0.24
    ä¸įèĥ½åĨį
    -0.23
    å®ĥçļĦ
    -0.23
    åľ¨è¿ĻéĩĮ
    -0.23
    è¿Ļä¸Ģ次
    -0.22
    å·²ç»ı
    -0.22
    åĽłä¸ºå®ĥ
    -0.22
    POSITIVE LOGITS
    proper
    0.25
     properly
    0.24
     Microwave
    0.22
     proper
    0.22
    åĮºåĨħ
    0.21
    æĥ«
    0.20
    adena
    0.20
    åĵī
    0.20
    æĢ§å¼º
    0.20
     contacted
    0.20
    Activations Density 0.108%

    No Known Activations