© 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. 57
    Prev
    Next
    INDEX
    Explanations

    new to kit, learning, files, work, framework, Illustrator, Rails

    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
     кнопк
    -0.25
     заÑĢегиÑģÑĤ
    -0.25
     dashes
    -0.24
     DÅ©ng
    -0.24
    åij¼åºĶ
    -0.23
    çªģåĩº
    -0.22
    åħģ
    -0.21
    åĩ¸æĺ¾
    -0.21
     безопаÑģн
    -0.21
     bg
    -0.21
    POSITIVE LOGITS
     myself
    0.46
    对æĪijæĿ¥è¯´
    0.33
    åĽłä¸ºæĪij
    0.33
    æĪijèĩªå·±
    0.32
     überhaupt
    0.32
    æĪijè¿ĺ
    0.30
    æĪij羣çļĦ
    0.30
     professionally
    0.30
    åľ¨æĪijçļĦ
    0.29
    第ä¸Ģ次
    0.29
    Activations Density 0.144%

    No Known Activations