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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 605
    Prev
    Next
    INDEX
    Explanations

    at anytime or on request

    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
    è¿ĻçĤ¹
    -0.26
    èݨ
    -0.26
    å¤ĸ表
    -0.25
    失æݧ
    -0.25
    èĢģçīĮ
    -0.24
    Ø£ÙĪضاع
    -0.23
     gorgeous
    -0.22
    vae
    -0.22
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.22
    çļĦ人æĿ¥è¯´
    -0.22
    POSITIVE LOGITS
     consultation
    0.28
     appropriate
    0.27
     haste
    0.26
     satisfactory
    0.26
     either
    0.26
    orio
    0.24
     consulta
    0.24
     Benton
    0.23
     nữa
    0.23
    æŁ¥æĺİ
    0.23
    Activations Density 0.035%

    No Known Activations