© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 323
    Prev
    Next
    INDEX
    Explanations

    recent developments and modern history

    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
    侧éĿ¢
    -0.27
     side
    -0.26
     verdict
    -0.23
    ãģ¾ãģ¾
    -0.23
    labs
    -0.23
    _side
    -0.23
    side
    -0.23
    ä¹łæĥ¯
    -0.23
    رد
    -0.23
    侧
    -0.22
    POSITIVE LOGITS
     renewed
    0.31
    æīįåıijçİ°
    0.30
    -begin
    0.29
     beginning
    0.28
    æŃ£å¼ıåIJ¯åĬ¨
    0.28
     intensified
    0.27
     onwards
    0.27
    忽çĦ¶
    0.26
    å¼Ģå§ĭ
    0.26
    å¹´å¼Ģå§ĭ
    0.25
    Activations Density 0.283%

    No Known Activations