© 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. 394
    Prev
    Next
    INDEX
    Explanations

    seeking confirmation or agreement

    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
    æĪĸ
    -0.26
    éľĢ
    -0.25
    rew
    -0.25
    æĢ¥éľĢ
    -0.24
    äºĨä¸Ģ
    -0.24
    ID
    -0.24
    建
    -0.23
    ',)↵
    -0.23
    缸
    -0.23
    ç«Ł
    -0.23
    POSITIVE LOGITS
     ведÑĮ
    0.33
     же
    0.23
    é©·
    0.23
    ãģłãģ£ãģ¦
    0.23
     przecież
    0.21
    ØŁ
    0.21
     mesmo
    0.21
    ?!↵↵
    0.21
    -dess
    0.21
    çīĮåŃIJ
    0.21
    Activations Density 0.011%

    No Known Activations