© 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. 545
    Prev
    Next
    INDEX
    Explanations

    keeping occupied and entertained

    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
    isko
    -0.28
    ertz
    -0.24
    aped
    -0.24
    -sided
    -0.23
    人家
    -0.23
    ä¹³
    -0.23
    象
    -0.22
    paring
    -0.21
    (axis
    -0.21
    aping
    -0.21
    POSITIVE LOGITS
     entertained
    0.38
     entertainment
    0.34
     entertain
    0.33
    娱ä¹IJ
    0.33
     distraction
    0.29
     distract
    0.29
    거리
    0.29
    /games
    0.28
    å¨Ľæ¨Ĥ
    0.28
    æļĩ
    0.28
    Activations Density 0.037%

    No Known Activations