© 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. 730
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
    ä¹Łæĺ¯ä¸Ģ个
    -0.25
    æŃ¥è¡Į
    -0.25
    æľĢåħ³éĶ®çļĦ
    -0.23
    iac
    -0.23
    é«ĺ涨
    -0.22
     gast
    -0.22
    encode
    -0.22
    yll
    -0.22
    engl
    -0.22
     Bernard
    -0.21
    POSITIVE LOGITS
     therefore
    0.62
    åĽłæѤ
    0.54
     accordingly
    0.47
     hence
    0.42
     поÑįÑĤомÑĥ
    0.41
    åĽłèĢĮ
    0.40
     donc
    0.40
    Therefore
    0.38
     daher
    0.38
     quindi
    0.37
    Activations Density 0.134%

    No Known Activations