© 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. 1044
    Prev
    Next
    INDEX
    Explanations

    think tank organization foundation institute

    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
     superintendent
    -0.25
     Superintendent
    -0.25
    Forms
    -0.24
    ä¸Ģ代
    -0.23
     asympt
    -0.23
     mentally
    -0.23
    èIJ¥ä¸ļ
    -0.22
    athers
    -0.22
    è·¸
    -0.22
     ÑģÑĥдеб
    -0.22
    POSITIVE LOGITS
     Institution
    0.30
    æľºæŀĦ
    0.29
     Institutions
    0.29
    åĽ½éĺ²
    0.28
    çłĶ究
    0.28
    åĨĽäºĭ
    0.26
    çłĶ究åijĺ
    0.26
     fellows
    0.26
    æĻºåºĵ
    0.26
    å¤§åĽ½
    0.25
    Activations Density 0.029%

    No Known Activations