© 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. 334
    Prev
    Next
    INDEX
    Explanations

    pricing and availability

    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
    ä¸Ģå®ļç¨ĭ度
    -0.26
     ponder
    -0.22
    SES
    -0.22
    ĵį
    -0.21
     humans
    -0.21
    ç½ijç«Ļé¦ĸ页
    -0.21
    管çIJĨèĢħ
    -0.21
    绣
    -0.21
    ä»ħä»ħ
    -0.21
    两次
    -0.21
    POSITIVE LOGITS
    ullet
    0.31
    åħ·ä½ĵçļĦ
    0.27
    çļĦåħ·ä½ĵ
    0.26
    åIJĪéĢĤçļĦ
    0.26
    éĢĤåIJĪ
    0.26
     appropriate
    0.26
    åIJĪéĢĤ
    0.25
    妥
    0.25
    æĤ¨çļĦ
    0.25
    æĽ´éĢĤåIJĪ
    0.25
    Activations Density 0.039%

    No Known Activations