© 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. 963
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and participles

    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
    幸
    -0.24
    fire
    -0.22
    å¼Ħ
    -0.22
    æ²»å®ī
    -0.22
    æľĽ
    -0.22
     MainPage
    -0.21
    宾
    -0.21
    鼶
    -0.21
    å®Ī
    -0.21
    åĨĴ
    -0.21
    POSITIVE LOGITS
     demonstrated
    0.31
    éĤ£æł·
    0.28
    æīĢ示
    0.28
     shown
    0.27
    ä¼ĹæīĢ
    0.27
     explained
    0.27
     done
    0.26
     váºŃy
    0.25
     duly
    0.25
     пÑĢедÑĥÑģмоÑĤÑĢ
    0.25
    Activations Density 0.084%

    No Known Activations