© 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. 774
    Prev
    Next
    INDEX
    Explanations

    surname endings

    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
    å¹²èѦ
    -0.28
    åĢ¼å¾Ĺ
    -0.24
     Worth
    -0.24
     worth
    -0.23
    èĶļ
    -0.22
    æĺ¯ä¸Ģ件
    -0.22
    ling
    -0.21
     spark
    -0.21
     Lange
    -0.21
    eam
    -0.21
    POSITIVE LOGITS
     tut
    0.27
     rub
    0.25
     uncomment
    0.25
    æ¶ħ
    0.24
    大å¸Ī
    0.24
    æĭĤ
    0.23
     Kings
    0.22
    天é¹ħ
    0.22
    _exceptions
    0.22
    æĪIJåIJį
    0.22
    Activations Density 0.003%

    No Known Activations