© 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. 136
    Prev
    Next
    INDEX
    Explanations

    statements and speech acts

    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
    éĢłç¦ı
    -0.34
     inex
    -0.26
     enroll
    -0.26
    éķ¿å¤§äºĨ
    -0.25
     enrollment
    -0.25
    loh
    -0.25
    æīİæł¹
    -0.24
    çĶŁæľº
    -0.24
     enrol
    -0.24
     Kee
    -0.24
    POSITIVE LOGITS
    è¨Ģ论
    0.46
    讲è¯Ŀ
    0.38
    表述
    0.36
    è¨Ģè¡Į
    0.36
    表æĢģ
    0.36
    ä¸Ģåı¥
    0.35
     publicly
    0.35
     quotes
    0.35
    è¨Ģè¯Ń
    0.35
    åħ¬å¼Ģ
    0.35
    Activations Density 0.181%

    No Known Activations